2024-08-06 14:23:41,782 INFO [trainer.py:870] (3/8) Training started
2024-08-06 14:23:41,783 INFO [trainer.py:889] (3/8) Device: cuda:3
2024-08-06 14:23:41,783 INFO [trainer.py:890] (3/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 100, 'reset_interval': 200, 'valid_interval': 2000, 'env_info': {'k2-version': '1.24.3', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '279b0c87015a615b81b147251814d737a548f397', 'k2-git-date': 'Wed May 24 22:24:09 2023', 'lhotse-version': '1.26.0', 'torch-version': '2.0.1+cu118', 'torch-cuda-available': True, 'torch-cuda-version': '11.8', 'python-version': '3.10', 'icefall-git-branch': None, 'icefall-git-sha1': None, 'icefall-git-date': None, 'icefall-path': '/workspace/icefall_llm', 'k2-path': '/usr/local/lib/python3.10/dist-packages/k2/__init__.py', 'lhotse-path': '/usr/local/lib/python3.10/dist-packages/lhotse/__init__.py', 'hostname': '6867463', 'IP address': '0.104.202.7'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 100, 'start_batch': 0, 'exp_dir': PosixPath('exp/valle'), 'optimizer_name': 'ScaledAdam', 'scheduler_name': 'Eden', 'base_lr': 0.03, 'warmup_steps': 200, 'seed': 42, 'inf_check': False, 'save_every_n': 100000, 'keep_last_k': 20, 'average_period': 0, 'accumulate_grad_steps': 2, 'dtype': 'float32', 'filter_min_duration': 0.5, 'filter_max_duration': 14.0, 'train_stage': 2, 'visualize': False, 'oom_check': False, 'model_name': 'valle', 'decoder_dim': 1024, 'nhead': 16, 'num_decoder_layers': 12, 'scale_factor': 1.0, 'norm_first': True, 'add_prenet': False, 'prefix_mode': 1, 'share_embedding': True, 'prepend_bos': False, 'num_quantizers': 8, 'scaling_xformers': False, 'manifest_dir': PosixPath('data/tokenized'), 'max_duration': 160, 'bucketing_sampler': True, 'num_buckets': 6, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 0.1, 'on_the_fly_feats': False, 'shuffle': True, 'buffer_size': 40000, 'shuffle_buffer_size': 100000, 'drop_last': False, 'return_cuts': True, 'num_workers': 8, 'enable_spec_aug': False, 'spec_aug_time_warp_factor': 80, 'input_strategy': 'PrecomputedFeatures', 'dataset': 'libritts', 'text_tokens': 'data/tokenized/unique_text_tokens.k2symbols', 'sampling_rate': 24000}
2024-08-06 14:23:41,784 INFO [trainer.py:892] (3/8) About to create model
2024-08-06 14:23:42,485 INFO [trainer.py:899] (3/8) Number of model parameters: 367386628
2024-08-06 14:23:42,485 INFO [checkpoint.py:112] (3/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,413 INFO [trainer.py:914] (3/8) Using DDP
2024-08-06 14:23:49,643 INFO [datamodule.py:427] (3/8) About to get train cuts
2024-08-06 14:23:49,644 INFO [datamodule.py:434] (3/8) About to get dev cuts
2024-08-06 14:23:49,645 INFO [datamodule.py:292] (3/8) Disable SpecAugment
2024-08-06 14:23:49,645 INFO [datamodule.py:294] (3/8) About to create train dataset
2024-08-06 14:23:49,646 INFO [datamodule.py:323] (3/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,272 INFO [datamodule.py:344] (3/8) About to create train dataloader
2024-08-06 14:23:50,272 INFO [datamodule.py:367] (3/8) About to create dev dataset
2024-08-06 14:23:50,606 INFO [datamodule.py:388] (3/8) About to create dev dataloader
2024-08-06 14:24:38,248 INFO [trainer.py:765] (3/8) Epoch 1, batch 100, train_loss[loss=106.9, NarTop10Accuracy=0.02041, over 7170.00 frames. ], tot_loss[loss=73.89, NarTop10Accuracy=0.04719, over 2363.47 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,518 INFO [trainer.py:765] (3/8) Epoch 1, batch 200, train_loss[loss=131.2, NarTop10Accuracy=0.01516, over 6537.00 frames. ], tot_loss[loss=97.39, NarTop10Accuracy=0.04203, over 3863.13 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,110 INFO [trainer.py:765] (3/8) Epoch 1, batch 300, train_loss[loss=108, NarTop10Accuracy=0.02065, over 7017.00 frames. ], tot_loss[loss=85.18, NarTop10Accuracy=0.04247, over 4669.78 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,482 INFO [trainer.py:765] (3/8) Epoch 1, batch 400, train_loss[loss=51.92, NarTop10Accuracy=0.02073, over 5241.00 frames. ], tot_loss[loss=67.91, NarTop10Accuracy=0.04635, over 5113.19 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,357 INFO [trainer.py:765] (3/8) Epoch 1, batch 500, train_loss[loss=14.39, NarTop10Accuracy=0.0267, over 6054.00 frames. ], tot_loss[loss=48.97, NarTop10Accuracy=0.05035, over 5400.32 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:04,000 INFO [trainer.py:765] (3/8) Epoch 1, batch 600, train_loss[loss=6.159, NarTop10Accuracy=0.2001, over 5730.00 frames. ], tot_loss[loss=33.44, NarTop10Accuracy=0.0552, over 5655.01 frames. ], batch size: 9, lr: 2.99e-02
2024-08-06 14:27:39,490 INFO [trainer.py:765] (3/8) Epoch 1, batch 700, train_loss[loss=6.731, NarTop10Accuracy=0.1201, over 4356.00 frames. ], tot_loss[loss=23.39, NarTop10Accuracy=0.06443, over 5733.59 frames. ], batch size: 5, lr: 2.99e-02
2024-08-06 14:28:08,831 INFO [trainer.py:765] (3/8) Epoch 1, batch 800, train_loss[loss=6.471, NarTop10Accuracy=0.1302, over 5175.00 frames. ], tot_loss[loss=17.17, NarTop10Accuracy=0.08574, over 5774.24 frames. ], batch size: 6, lr: 2.98e-02
2024-08-06 14:28:36,759 INFO [trainer.py:765] (3/8) Epoch 1, batch 900, train_loss[loss=5.776, NarTop10Accuracy=0.1791, over 6234.00 frames. ], tot_loss[loss=12.81, NarTop10Accuracy=0.1125, over 5782.77 frames. ], batch size: 13, lr: 2.98e-02
2024-08-06 14:29:12,585 INFO [trainer.py:765] (3/8) Epoch 1, batch 1000, train_loss[loss=5.751, NarTop10Accuracy=0.1824, over 6231.00 frames. ], tot_loss[loss=10.12, NarTop10Accuracy=0.1331, over 5890.08 frames. ], batch size: 13, lr: 2.97e-02
2024-08-06 14:29:42,824 INFO [trainer.py:765] (3/8) Epoch 1, batch 1100, train_loss[loss=5.623, NarTop10Accuracy=0.2068, over 6945.00 frames. ], tot_loss[loss=8.423, NarTop10Accuracy=0.1521, over 5927.44 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,467 INFO [trainer.py:765] (3/8) Epoch 1, batch 1200, train_loss[loss=5.859, NarTop10Accuracy=0.1813, over 7272.00 frames. ], tot_loss[loss=7.355, NarTop10Accuracy=0.17, over 5922.68 frames. ], batch size: 31, lr: 2.96e-02
2024-08-06 14:30:48,746 INFO [trainer.py:765] (3/8) Epoch 1, batch 1300, train_loss[loss=5.288, NarTop10Accuracy=0.2874, over 4920.00 frames. ], tot_loss[loss=6.68, NarTop10Accuracy=0.1871, over 5984.21 frames. ], batch size: 6, lr: 2.95e-02
2024-08-06 14:31:18,143 INFO [trainer.py:765] (3/8) Epoch 1, batch 1400, train_loss[loss=5.618, NarTop10Accuracy=0.2033, over 6171.00 frames. ], tot_loss[loss=6.252, NarTop10Accuracy=0.197, over 6019.76 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,025 INFO [trainer.py:765] (3/8) Epoch 1, batch 1500, train_loss[loss=5.769, NarTop10Accuracy=0.187, over 6066.00 frames. ], tot_loss[loss=5.979, NarTop10Accuracy=0.2074, over 5962.70 frames. ], batch size: 51, lr: 2.94e-02
2024-08-06 14:32:13,691 INFO [trainer.py:765] (3/8) Epoch 1, batch 1600, train_loss[loss=5.613, NarTop10Accuracy=0.2, over 6984.00 frames. ], tot_loss[loss=5.787, NarTop10Accuracy=0.2178, over 5935.75 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,198 INFO [trainer.py:765] (3/8) Epoch 1, batch 1700, train_loss[loss=5.363, NarTop10Accuracy=0.2575, over 6273.00 frames. ], tot_loss[loss=5.665, NarTop10Accuracy=0.2248, over 5939.13 frames. ], batch size: 13, lr: 2.92e-02
2024-08-06 14:33:06,498 INFO [trainer.py:765] (3/8) Epoch 1, batch 1800, train_loss[loss=5.5, NarTop10Accuracy=0.2237, over 7002.00 frames. ], tot_loss[loss=5.573, NarTop10Accuracy=0.2331, over 6006.15 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,623 INFO [trainer.py:765] (3/8) Epoch 1, batch 1900, train_loss[loss=5.66, NarTop10Accuracy=0.1961, over 6279.00 frames. ], tot_loss[loss=5.503, NarTop10Accuracy=0.2415, over 6042.82 frames. ], batch size: 50, lr: 2.90e-02
2024-08-06 14:33:58,014 INFO [trainer.py:765] (3/8) Epoch 1, batch 2000, train_loss[loss=5.471, NarTop10Accuracy=0.2504, over 6885.00 frames. ], tot_loss[loss=5.448, NarTop10Accuracy=0.2492, over 6018.24 frames. ], batch size: 50, lr: 2.89e-02
2024-08-06 14:33:58,015 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (3/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 26959MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 4.749e+01 2.278e+02 7.300e+02 1.664e+04 7.177e+05, threshold=1.460e+03, percent-clipped=0.0
2024-08-06 14:34:32,061 INFO [trainer.py:765] (3/8) Epoch 1, batch 2100, train_loss[loss=5.002, NarTop10Accuracy=0.3485, over 4056.00 frames. ], tot_loss[loss=5.39, NarTop10Accuracy=0.2587, over 5994.28 frames. ], batch size: 4, lr: 2.88e-02
2024-08-06 14:34:57,305 INFO [trainer.py:765] (3/8) Epoch 1, batch 2200, train_loss[loss=5.54, NarTop10Accuracy=0.2302, over 7410.00 frames. ], tot_loss[loss=5.35, NarTop10Accuracy=0.2642, over 6026.31 frames. ], batch size: 32, lr: 2.87e-02
2024-08-06 14:35:22,457 INFO [trainer.py:765] (3/8) Epoch 1, batch 2300, train_loss[loss=5.268, NarTop10Accuracy=0.2786, over 5592.00 frames. ], tot_loss[loss=5.344, NarTop10Accuracy=0.265, over 6026.29 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,816 INFO [trainer.py:765] (3/8) Epoch 1, batch 2400, train_loss[loss=5.384, NarTop10Accuracy=0.2511, over 5064.00 frames. ], tot_loss[loss=5.284, NarTop10Accuracy=0.2759, over 5767.57 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,409 INFO [trainer.py:765] (3/8) Epoch 1, batch 2500, train_loss[loss=5.011, NarTop10Accuracy=0.3322, over 5235.00 frames. ], tot_loss[loss=5.221, NarTop10Accuracy=0.2875, over 5460.03 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:30,283 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 14:37:29,669 INFO [trainer.py:765] (3/8) Epoch 2, batch 100, train_loss[loss=4.971, NarTop10Accuracy=0.3324, over 7089.00 frames. ], tot_loss[loss=5.18, NarTop10Accuracy=0.296, over 2367.74 frames. ], batch size: 31, lr: 2.77e-02
2024-08-06 14:38:10,015 INFO [trainer.py:765] (3/8) Epoch 2, batch 200, train_loss[loss=5.128, NarTop10Accuracy=0.3059, over 6870.00 frames. ], tot_loss[loss=5.157, NarTop10Accuracy=0.3006, over 3852.99 frames. ], batch size: 17, lr: 2.76e-02
2024-08-06 14:38:38,297 INFO [trainer.py:765] (3/8) Epoch 2, batch 300, train_loss[loss=5.161, NarTop10Accuracy=0.3006, over 7041.00 frames. ], tot_loss[loss=5.131, NarTop10Accuracy=0.305, over 4660.18 frames. ], batch size: 22, lr: 2.75e-02
2024-08-06 14:39:06,999 INFO [trainer.py:765] (3/8) Epoch 2, batch 400, train_loss[loss=4.877, NarTop10Accuracy=0.3572, over 5094.00 frames. ], tot_loss[loss=5.107, NarTop10Accuracy=0.3088, over 5099.80 frames. ], batch size: 7, lr: 2.74e-02
2024-08-06 14:39:46,119 INFO [trainer.py:765] (3/8) Epoch 2, batch 500, train_loss[loss=5.073, NarTop10Accuracy=0.3074, over 6066.00 frames. ], tot_loss[loss=5.068, NarTop10Accuracy=0.3164, over 5361.27 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,083 INFO [trainer.py:765] (3/8) Epoch 2, batch 600, train_loss[loss=4.836, NarTop10Accuracy=0.3649, over 5637.00 frames. ], tot_loss[loss=5.048, NarTop10Accuracy=0.3204, over 5643.57 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,589 INFO [trainer.py:765] (3/8) Epoch 2, batch 700, train_loss[loss=4.947, NarTop10Accuracy=0.3464, over 5268.00 frames. ], tot_loss[loss=5.033, NarTop10Accuracy=0.3226, over 5706.94 frames. ], batch size: 6, lr: 2.70e-02
2024-08-06 14:41:24,514 INFO [trainer.py:765] (3/8) Epoch 2, batch 800, train_loss[loss=5.185, NarTop10Accuracy=0.2918, over 5154.00 frames. ], tot_loss[loss=5.028, NarTop10Accuracy=0.3236, over 5772.89 frames. ], batch size: 6, lr: 2.69e-02
2024-08-06 14:41:54,404 INFO [trainer.py:765] (3/8) Epoch 2, batch 900, train_loss[loss=4.671, NarTop10Accuracy=0.3893, over 6219.00 frames. ], tot_loss[loss=4.988, NarTop10Accuracy=0.3313, over 5787.03 frames. ], batch size: 13, lr: 2.68e-02
2024-08-06 14:42:23,902 INFO [trainer.py:765] (3/8) Epoch 2, batch 1000, train_loss[loss=4.658, NarTop10Accuracy=0.3945, over 6648.00 frames. ], tot_loss[loss=4.949, NarTop10Accuracy=0.3383, over 5890.09 frames. ], batch size: 14, lr: 2.66e-02
2024-08-06 14:42:56,256 INFO [trainer.py:765] (3/8) Epoch 2, batch 1100, train_loss[loss=5.171, NarTop10Accuracy=0.294, over 6819.00 frames. ], tot_loss[loss=4.937, NarTop10Accuracy=0.3409, over 5926.60 frames. ], batch size: 17, lr: 2.65e-02
2024-08-06 14:43:35,186 INFO [trainer.py:765] (3/8) Epoch 2, batch 1200, train_loss[loss=4.714, NarTop10Accuracy=0.3763, over 7338.00 frames. ], tot_loss[loss=4.903, NarTop10Accuracy=0.3468, over 5929.22 frames. ], batch size: 31, lr: 2.64e-02
2024-08-06 14:44:04,345 INFO [trainer.py:765] (3/8) Epoch 2, batch 1300, train_loss[loss=4.851, NarTop10Accuracy=0.3542, over 5190.00 frames. ], tot_loss[loss=4.862, NarTop10Accuracy=0.355, over 5989.94 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,727 INFO [trainer.py:765] (3/8) Epoch 2, batch 1400, train_loss[loss=4.706, NarTop10Accuracy=0.38, over 6114.00 frames. ], tot_loss[loss=4.854, NarTop10Accuracy=0.3564, over 6032.30 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,441 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (3/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 26959MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 6.328e+01 1.178e+02 1.410e+02 1.789e+02 6.269e+02, threshold=2.821e+02, percent-clipped=0.0
2024-08-06 14:45:09,806 INFO [trainer.py:765] (3/8) Epoch 2, batch 1500, train_loss[loss=4.851, NarTop10Accuracy=0.349, over 5994.00 frames. ], tot_loss[loss=4.83, NarTop10Accuracy=0.3609, over 5948.08 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,659 INFO [trainer.py:765] (3/8) Epoch 2, batch 1600, train_loss[loss=4.608, NarTop10Accuracy=0.4074, over 7395.00 frames. ], tot_loss[loss=4.805, NarTop10Accuracy=0.366, over 5922.73 frames. ], batch size: 23, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (3/8) Epoch 2, batch 1700, train_loss[loss=4.846, NarTop10Accuracy=0.3569, over 6678.00 frames. ], tot_loss[loss=4.798, NarTop10Accuracy=0.3671, over 5907.39 frames. ], batch size: 14, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (3/8) Epoch 2, batch 1800, train_loss[loss=4.67, NarTop10Accuracy=0.3978, over 7092.00 frames. ], tot_loss[loss=4.777, NarTop10Accuracy=0.371, over 5977.57 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (3/8) Epoch 2, batch 1900, train_loss[loss=4.66, NarTop10Accuracy=0.395, over 5892.00 frames. ], tot_loss[loss=4.754, NarTop10Accuracy=0.3756, over 6013.67 frames. ], batch size: 51, lr: 2.55e-02
2024-08-06 14:47:23,233 INFO [trainer.py:765] (3/8) Epoch 2, batch 2000, train_loss[loss=4.821, NarTop10Accuracy=0.3679, over 6018.00 frames. ], tot_loss[loss=4.729, NarTop10Accuracy=0.3801, over 5998.91 frames. ], batch size: 50, lr: 2.54e-02
2024-08-06 14:47:48,588 INFO [trainer.py:765] (3/8) Epoch 2, batch 2100, train_loss[loss=4.851, NarTop10Accuracy=0.3428, over 3855.00 frames. ], tot_loss[loss=4.711, NarTop10Accuracy=0.3835, over 5973.79 frames. ], batch size: 4, lr: 2.53e-02
2024-08-06 14:48:13,764 INFO [trainer.py:765] (3/8) Epoch 2, batch 2200, train_loss[loss=4.723, NarTop10Accuracy=0.377, over 7227.00 frames. ], tot_loss[loss=4.681, NarTop10Accuracy=0.3893, over 6017.31 frames. ], batch size: 31, lr: 2.51e-02
2024-08-06 14:48:38,951 INFO [trainer.py:765] (3/8) Epoch 2, batch 2300, train_loss[loss=4.805, NarTop10Accuracy=0.3645, over 5763.00 frames. ], tot_loss[loss=4.682, NarTop10Accuracy=0.389, over 6034.02 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,319 INFO [trainer.py:765] (3/8) Epoch 2, batch 2400, train_loss[loss=4.463, NarTop10Accuracy=0.4349, over 5268.00 frames. ], tot_loss[loss=4.638, NarTop10Accuracy=0.3973, over 5785.51 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,867 INFO [trainer.py:765] (3/8) Epoch 2, batch 2500, train_loss[loss=4.745, NarTop10Accuracy=0.3686, over 5265.00 frames. ], tot_loss[loss=4.616, NarTop10Accuracy=0.4014, over 5490.06 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,794 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 14:50:51,117 INFO [trainer.py:765] (3/8) Epoch 3, batch 100, train_loss[loss=4.759, NarTop10Accuracy=0.3726, over 7227.00 frames. ], tot_loss[loss=4.591, NarTop10Accuracy=0.4066, over 2359.95 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,388 INFO [trainer.py:765] (3/8) Epoch 3, batch 200, train_loss[loss=4.715, NarTop10Accuracy=0.3818, over 6876.00 frames. ], tot_loss[loss=4.538, NarTop10Accuracy=0.4172, over 3848.41 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,954 INFO [trainer.py:765] (3/8) Epoch 3, batch 300, train_loss[loss=4.663, NarTop10Accuracy=0.3947, over 7188.00 frames. ], tot_loss[loss=4.522, NarTop10Accuracy=0.42, over 4661.20 frames. ], batch size: 22, lr: 2.33e-02
2024-08-06 14:52:32,359 INFO [trainer.py:765] (3/8) Epoch 3, batch 400, train_loss[loss=4.549, NarTop10Accuracy=0.4217, over 4932.00 frames. ], tot_loss[loss=4.496, NarTop10Accuracy=0.4252, over 5110.33 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,680 INFO [trainer.py:765] (3/8) Epoch 3, batch 500, train_loss[loss=4.401, NarTop10Accuracy=0.4367, over 6081.00 frames. ], tot_loss[loss=4.492, NarTop10Accuracy=0.4256, over 5384.69 frames. ], batch size: 11, lr: 2.31e-02
2024-08-06 14:53:29,552 INFO [trainer.py:765] (3/8) Epoch 3, batch 600, train_loss[loss=4.214, NarTop10Accuracy=0.4836, over 5763.00 frames. ], tot_loss[loss=4.469, NarTop10Accuracy=0.4306, over 5640.79 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,466 INFO [trainer.py:765] (3/8) Epoch 3, batch 700, train_loss[loss=4.287, NarTop10Accuracy=0.4699, over 4260.00 frames. ], tot_loss[loss=4.442, NarTop10Accuracy=0.4363, over 5707.50 frames. ], batch size: 5, lr: 2.29e-02
2024-08-06 14:54:44,785 INFO [trainer.py:765] (3/8) Epoch 3, batch 800, train_loss[loss=4.179, NarTop10Accuracy=0.4841, over 4866.00 frames. ], tot_loss[loss=4.419, NarTop10Accuracy=0.4409, over 5764.05 frames. ], batch size: 6, lr: 2.28e-02
2024-08-06 14:54:58,686 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (3/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 14:55:07,182 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 8.443e+01 1.396e+02 1.639e+02 2.017e+02 7.124e+02, threshold=3.277e+02, percent-clipped=4.5
2024-08-06 14:55:21,051 INFO [trainer.py:765] (3/8) Epoch 3, batch 900, train_loss[loss=4.13, NarTop10Accuracy=0.4954, over 6222.00 frames. ], tot_loss[loss=4.39, NarTop10Accuracy=0.4465, over 5777.05 frames. ], batch size: 13, lr: 2.26e-02
2024-08-06 14:56:04,957 INFO [trainer.py:765] (3/8) Epoch 3, batch 1000, train_loss[loss=4.184, NarTop10Accuracy=0.4856, over 6600.00 frames. ], tot_loss[loss=4.37, NarTop10Accuracy=0.4504, over 5871.23 frames. ], batch size: 14, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (3/8) Epoch 3, batch 1100, train_loss[loss=4.56, NarTop10Accuracy=0.4058, over 6720.00 frames. ], tot_loss[loss=4.352, NarTop10Accuracy=0.454, over 5919.92 frames. ], batch size: 17, lr: 2.24e-02
2024-08-06 14:57:06,376 INFO [trainer.py:765] (3/8) Epoch 3, batch 1200, train_loss[loss=4.429, NarTop10Accuracy=0.4312, over 7431.00 frames. ], tot_loss[loss=4.335, NarTop10Accuracy=0.457, over 5932.99 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,630 INFO [trainer.py:765] (3/8) Epoch 3, batch 1300, train_loss[loss=4.24, NarTop10Accuracy=0.478, over 5070.00 frames. ], tot_loss[loss=4.306, NarTop10Accuracy=0.4623, over 5998.69 frames. ], batch size: 6, lr: 2.22e-02
2024-08-06 14:58:22,899 INFO [trainer.py:765] (3/8) Epoch 3, batch 1400, train_loss[loss=4.35, NarTop10Accuracy=0.459, over 6183.00 frames. ], tot_loss[loss=4.3, NarTop10Accuracy=0.4635, over 6019.73 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,854 INFO [trainer.py:765] (3/8) Epoch 3, batch 1500, train_loss[loss=4.35, NarTop10Accuracy=0.4504, over 6507.00 frames. ], tot_loss[loss=4.276, NarTop10Accuracy=0.4685, over 5960.82 frames. ], batch size: 50, lr: 2.20e-02
2024-08-06 14:59:18,714 INFO [trainer.py:765] (3/8) Epoch 3, batch 1600, train_loss[loss=3.903, NarTop10Accuracy=0.5533, over 6969.00 frames. ], tot_loss[loss=4.259, NarTop10Accuracy=0.4715, over 5939.72 frames. ], batch size: 22, lr: 2.19e-02
2024-08-06 14:59:45,951 INFO [trainer.py:765] (3/8) Epoch 3, batch 1700, train_loss[loss=4.173, NarTop10Accuracy=0.489, over 6273.00 frames. ], tot_loss[loss=4.234, NarTop10Accuracy=0.4766, over 5910.81 frames. ], batch size: 13, lr: 2.18e-02
2024-08-06 15:00:12,496 INFO [trainer.py:765] (3/8) Epoch 3, batch 1800, train_loss[loss=3.973, NarTop10Accuracy=0.5326, over 7131.00 frames. ], tot_loss[loss=4.214, NarTop10Accuracy=0.4808, over 5985.72 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,947 INFO [trainer.py:765] (3/8) Epoch 3, batch 1900, train_loss[loss=4.658, NarTop10Accuracy=0.3937, over 6606.00 frames. ], tot_loss[loss=4.195, NarTop10Accuracy=0.4848, over 6033.08 frames. ], batch size: 51, lr: 2.16e-02
2024-08-06 15:01:04,605 INFO [trainer.py:765] (3/8) Epoch 3, batch 2000, train_loss[loss=4.423, NarTop10Accuracy=0.4398, over 5751.00 frames. ], tot_loss[loss=4.167, NarTop10Accuracy=0.4903, over 6011.50 frames. ], batch size: 51, lr: 2.15e-02
2024-08-06 15:01:29,897 INFO [trainer.py:765] (3/8) Epoch 3, batch 2100, train_loss[loss=3.921, NarTop10Accuracy=0.5438, over 3936.00 frames. ], tot_loss[loss=4.143, NarTop10Accuracy=0.495, over 5980.16 frames. ], batch size: 4, lr: 2.14e-02
2024-08-06 15:01:55,182 INFO [trainer.py:765] (3/8) Epoch 3, batch 2200, train_loss[loss=3.935, NarTop10Accuracy=0.5495, over 7524.00 frames. ], tot_loss[loss=4.12, NarTop10Accuracy=0.5002, over 5998.18 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,410 INFO [trainer.py:765] (3/8) Epoch 3, batch 2300, train_loss[loss=4.43, NarTop10Accuracy=0.4342, over 5583.00 frames. ], tot_loss[loss=4.134, NarTop10Accuracy=0.4971, over 6008.71 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,664 INFO [trainer.py:765] (3/8) Epoch 3, batch 2400, train_loss[loss=4.217, NarTop10Accuracy=0.471, over 5049.00 frames. ], tot_loss[loss=4.1, NarTop10Accuracy=0.5041, over 5756.50 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,235 INFO [trainer.py:765] (3/8) Epoch 3, batch 2500, train_loss[loss=3.711, NarTop10Accuracy=0.5866, over 5178.00 frames. ], tot_loss[loss=4.052, NarTop10Accuracy=0.5141, over 5464.40 frames. ], batch size: 7, lr: 2.10e-02
2024-08-06 15:03:28,358 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 15:04:28,131 INFO [trainer.py:765] (3/8) Epoch 4, batch 100, train_loss[loss=3.926, NarTop10Accuracy=0.5423, over 7152.00 frames. ], tot_loss[loss=4.029, NarTop10Accuracy=0.5185, over 2356.16 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,843 INFO [trainer.py:765] (3/8) Epoch 4, batch 200, train_loss[loss=3.758, NarTop10Accuracy=0.5806, over 6726.00 frames. ], tot_loss[loss=4.009, NarTop10Accuracy=0.523, over 3859.81 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,509 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (3/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,694 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:05:36,237 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.166e+02 1.765e+02 1.975e+02 2.270e+02 5.852e+02, threshold=3.949e+02, percent-clipped=2.8
2024-08-06 15:05:43,888 INFO [trainer.py:765] (3/8) Epoch 4, batch 300, train_loss[loss=3.786, NarTop10Accuracy=0.5727, over 7053.00 frames. ], tot_loss[loss=3.996, NarTop10Accuracy=0.5254, over 4657.93 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,123 INFO [trainer.py:765] (3/8) Epoch 4, batch 400, train_loss[loss=3.824, NarTop10Accuracy=0.5616, over 5145.00 frames. ], tot_loss[loss=4.008, NarTop10Accuracy=0.5235, over 5111.08 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,473 INFO [trainer.py:765] (3/8) Epoch 4, batch 500, train_loss[loss=3.968, NarTop10Accuracy=0.5243, over 6000.00 frames. ], tot_loss[loss=3.987, NarTop10Accuracy=0.5275, over 5387.25 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,817 INFO [trainer.py:765] (3/8) Epoch 4, batch 600, train_loss[loss=3.773, NarTop10Accuracy=0.5702, over 5736.00 frames. ], tot_loss[loss=3.979, NarTop10Accuracy=0.5295, over 5651.51 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,001 INFO [trainer.py:765] (3/8) Epoch 4, batch 700, train_loss[loss=4.209, NarTop10Accuracy=0.4689, over 5010.00 frames. ], tot_loss[loss=3.972, NarTop10Accuracy=0.5302, over 5723.87 frames. ], batch size: 6, lr: 1.92e-02
2024-08-06 15:08:32,430 INFO [trainer.py:765] (3/8) Epoch 4, batch 800, train_loss[loss=3.729, NarTop10Accuracy=0.5754, over 5055.00 frames. ], tot_loss[loss=3.959, NarTop10Accuracy=0.5326, over 5789.04 frames. ], batch size: 6, lr: 1.91e-02
2024-08-06 15:09:10,690 INFO [trainer.py:765] (3/8) Epoch 4, batch 900, train_loss[loss=3.626, NarTop10Accuracy=0.6057, over 6738.00 frames. ], tot_loss[loss=3.921, NarTop10Accuracy=0.5404, over 5799.40 frames. ], batch size: 14, lr: 1.90e-02
2024-08-06 15:09:46,076 INFO [trainer.py:765] (3/8) Epoch 4, batch 1000, train_loss[loss=3.673, NarTop10Accuracy=0.6006, over 6141.00 frames. ], tot_loss[loss=3.917, NarTop10Accuracy=0.5419, over 5898.60 frames. ], batch size: 13, lr: 1.89e-02
2024-08-06 15:10:18,139 INFO [trainer.py:765] (3/8) Epoch 4, batch 1100, train_loss[loss=3.794, NarTop10Accuracy=0.5672, over 6867.00 frames. ], tot_loss[loss=3.913, NarTop10Accuracy=0.5428, over 5920.26 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,075 INFO [trainer.py:765] (3/8) Epoch 4, batch 1200, train_loss[loss=4.321, NarTop10Accuracy=0.4597, over 7107.00 frames. ], tot_loss[loss=3.907, NarTop10Accuracy=0.5435, over 5924.51 frames. ], batch size: 31, lr: 1.88e-02
2024-08-06 15:11:32,074 INFO [trainer.py:765] (3/8) Epoch 4, batch 1300, train_loss[loss=3.6, NarTop10Accuracy=0.6067, over 4395.00 frames. ], tot_loss[loss=3.87, NarTop10Accuracy=0.5511, over 5978.85 frames. ], batch size: 5, lr: 1.87e-02
2024-08-06 15:12:05,688 INFO [trainer.py:765] (3/8) Epoch 4, batch 1400, train_loss[loss=3.66, NarTop10Accuracy=0.6048, over 6117.00 frames. ], tot_loss[loss=3.864, NarTop10Accuracy=0.5524, over 6004.96 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (3/8) Epoch 4, batch 1500, train_loss[loss=3.783, NarTop10Accuracy=0.5715, over 6213.00 frames. ], tot_loss[loss=3.864, NarTop10Accuracy=0.5523, over 5951.38 frames. ], batch size: 50, lr: 1.85e-02
2024-08-06 15:13:01,510 INFO [trainer.py:765] (3/8) Epoch 4, batch 1600, train_loss[loss=3.856, NarTop10Accuracy=0.5563, over 7092.00 frames. ], tot_loss[loss=3.855, NarTop10Accuracy=0.5541, over 5936.00 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,133 INFO [trainer.py:765] (3/8) Epoch 4, batch 1700, train_loss[loss=3.684, NarTop10Accuracy=0.5752, over 6606.00 frames. ], tot_loss[loss=3.822, NarTop10Accuracy=0.5605, over 5908.85 frames. ], batch size: 14, lr: 1.84e-02
2024-08-06 15:13:54,557 INFO [trainer.py:765] (3/8) Epoch 4, batch 1800, train_loss[loss=3.813, NarTop10Accuracy=0.5621, over 6975.00 frames. ], tot_loss[loss=3.826, NarTop10Accuracy=0.5599, over 5968.20 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,998 INFO [trainer.py:765] (3/8) Epoch 4, batch 1900, train_loss[loss=3.708, NarTop10Accuracy=0.583, over 6249.00 frames. ], tot_loss[loss=3.847, NarTop10Accuracy=0.5554, over 6025.23 frames. ], batch size: 51, lr: 1.82e-02
2024-08-06 15:14:46,672 INFO [trainer.py:765] (3/8) Epoch 4, batch 2000, train_loss[loss=3.708, NarTop10Accuracy=0.5845, over 6033.00 frames. ], tot_loss[loss=3.826, NarTop10Accuracy=0.56, over 5988.99 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,859 INFO [trainer.py:765] (3/8) Epoch 4, batch 2100, train_loss[loss=3.602, NarTop10Accuracy=0.6083, over 3864.00 frames. ], tot_loss[loss=3.813, NarTop10Accuracy=0.5628, over 5966.04 frames. ], batch size: 4, lr: 1.81e-02
2024-08-06 15:15:37,089 INFO [trainer.py:765] (3/8) Epoch 4, batch 2200, train_loss[loss=3.697, NarTop10Accuracy=0.5911, over 7356.00 frames. ], tot_loss[loss=3.805, NarTop10Accuracy=0.5642, over 6007.44 frames. ], batch size: 31, lr: 1.80e-02
2024-08-06 15:15:55,089 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:16:03,243 INFO [trainer.py:811] (3/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:16:03,740 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.414e+02 1.889e+02 2.096e+02 2.369e+02 1.168e+03, threshold=4.192e+02, percent-clipped=1.7
2024-08-06 15:16:10,347 INFO [trainer.py:765] (3/8) Epoch 4, batch 2300, train_loss[loss=3.762, NarTop10Accuracy=0.581, over 5739.00 frames. ], tot_loss[loss=3.812, NarTop10Accuracy=0.5627, over 6023.78 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,840 INFO [trainer.py:765] (3/8) Epoch 4, batch 2400, train_loss[loss=3.622, NarTop10Accuracy=0.6116, over 4968.00 frames. ], tot_loss[loss=3.781, NarTop10Accuracy=0.5687, over 5776.93 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,535 INFO [trainer.py:765] (3/8) Epoch 4, batch 2500, train_loss[loss=3.412, NarTop10Accuracy=0.6493, over 5310.00 frames. ], tot_loss[loss=3.769, NarTop10Accuracy=0.5709, over 5483.44 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,222 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 15:18:24,101 INFO [trainer.py:765] (3/8) Epoch 5, batch 100, train_loss[loss=3.601, NarTop10Accuracy=0.6061, over 7134.00 frames. ], tot_loss[loss=3.778, NarTop10Accuracy=0.5692, over 2371.62 frames. ], batch size: 31, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (3/8) Epoch 5, batch 200, train_loss[loss=4.051, NarTop10Accuracy=0.5079, over 6831.00 frames. ], tot_loss[loss=3.768, NarTop10Accuracy=0.5712, over 3863.67 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,888 INFO [trainer.py:765] (3/8) Epoch 5, batch 300, train_loss[loss=3.981, NarTop10Accuracy=0.5203, over 7203.00 frames. ], tot_loss[loss=3.728, NarTop10Accuracy=0.5796, over 4672.07 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,656 INFO [trainer.py:765] (3/8) Epoch 5, batch 400, train_loss[loss=3.554, NarTop10Accuracy=0.6122, over 5139.00 frames. ], tot_loss[loss=3.721, NarTop10Accuracy=0.5807, over 5117.47 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,299 INFO [trainer.py:765] (3/8) Epoch 5, batch 500, train_loss[loss=3.851, NarTop10Accuracy=0.5498, over 6018.00 frames. ], tot_loss[loss=3.734, NarTop10Accuracy=0.5777, over 5388.25 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,711 INFO [trainer.py:765] (3/8) Epoch 5, batch 600, train_loss[loss=3.941, NarTop10Accuracy=0.5293, over 5586.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.5803, over 5662.46 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (3/8) Epoch 5, batch 700, train_loss[loss=3.328, NarTop10Accuracy=0.6604, over 5028.00 frames. ], tot_loss[loss=3.723, NarTop10Accuracy=0.5806, over 5720.40 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,499 INFO [trainer.py:765] (3/8) Epoch 5, batch 800, train_loss[loss=4.127, NarTop10Accuracy=0.5028, over 5115.00 frames. ], tot_loss[loss=3.709, NarTop10Accuracy=0.5832, over 5777.23 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,783 INFO [trainer.py:765] (3/8) Epoch 5, batch 900, train_loss[loss=3.575, NarTop10Accuracy=0.6153, over 6231.00 frames. ], tot_loss[loss=3.692, NarTop10Accuracy=0.5862, over 5793.96 frames. ], batch size: 13, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (3/8) Epoch 5, batch 1000, train_loss[loss=3.483, NarTop10Accuracy=0.634, over 6135.00 frames. ], tot_loss[loss=3.682, NarTop10Accuracy=0.5884, over 5889.89 frames. ], batch size: 13, lr: 1.60e-02
2024-08-06 15:24:09,572 INFO [trainer.py:765] (3/8) Epoch 5, batch 1100, train_loss[loss=3.457, NarTop10Accuracy=0.6466, over 6738.00 frames. ], tot_loss[loss=3.68, NarTop10Accuracy=0.5891, over 5929.09 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,528 INFO [trainer.py:765] (3/8) Epoch 5, batch 1200, train_loss[loss=3.478, NarTop10Accuracy=0.6265, over 7281.00 frames. ], tot_loss[loss=3.671, NarTop10Accuracy=0.5907, over 5916.28 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,380 INFO [trainer.py:765] (3/8) Epoch 5, batch 1300, train_loss[loss=3.893, NarTop10Accuracy=0.5524, over 5175.00 frames. ], tot_loss[loss=3.662, NarTop10Accuracy=0.5928, over 5992.41 frames. ], batch size: 6, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (3/8) Epoch 5, batch 1400, train_loss[loss=3.963, NarTop10Accuracy=0.5219, over 6015.00 frames. ], tot_loss[loss=3.668, NarTop10Accuracy=0.5917, over 6023.84 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,195 INFO [trainer.py:765] (3/8) Epoch 5, batch 1500, train_loss[loss=3.681, NarTop10Accuracy=0.5965, over 5886.00 frames. ], tot_loss[loss=3.67, NarTop10Accuracy=0.5905, over 5953.97 frames. ], batch size: 50, lr: 1.58e-02
2024-08-06 15:26:54,131 INFO [trainer.py:765] (3/8) Epoch 5, batch 1600, train_loss[loss=3.465, NarTop10Accuracy=0.6328, over 7401.00 frames. ], tot_loss[loss=3.679, NarTop10Accuracy=0.5889, over 5918.20 frames. ], batch size: 24, lr: 1.57e-02
2024-08-06 15:27:19,604 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (3/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.340e+02 1.756e+02 1.962e+02 2.205e+02 5.880e+02, threshold=3.924e+02, percent-clipped=0.8
2024-08-06 15:27:29,131 INFO [trainer.py:765] (3/8) Epoch 5, batch 1700, train_loss[loss=3.75, NarTop10Accuracy=0.5819, over 6255.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5912, over 5909.71 frames. ], batch size: 13, lr: 1.56e-02
2024-08-06 15:27:55,653 INFO [trainer.py:765] (3/8) Epoch 5, batch 1800, train_loss[loss=3.797, NarTop10Accuracy=0.5567, over 7170.00 frames. ], tot_loss[loss=3.661, NarTop10Accuracy=0.5929, over 5962.49 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,172 INFO [trainer.py:765] (3/8) Epoch 5, batch 1900, train_loss[loss=3.723, NarTop10Accuracy=0.5838, over 5931.00 frames. ], tot_loss[loss=3.666, NarTop10Accuracy=0.5916, over 6008.76 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (3/8) Epoch 5, batch 2000, train_loss[loss=3.579, NarTop10Accuracy=0.6116, over 6921.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5918, over 5988.93 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:29:13,770 INFO [trainer.py:765] (3/8) Epoch 5, batch 2100, train_loss[loss=3.358, NarTop10Accuracy=0.6604, over 3915.00 frames. ], tot_loss[loss=3.682, NarTop10Accuracy=0.5877, over 5965.24 frames. ], batch size: 4, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (3/8) Epoch 5, batch 2200, train_loss[loss=4.205, NarTop10Accuracy=0.4793, over 7188.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.5918, over 6007.97 frames. ], batch size: 31, lr: 1.54e-02
2024-08-06 15:30:04,430 INFO [trainer.py:765] (3/8) Epoch 5, batch 2300, train_loss[loss=3.504, NarTop10Accuracy=0.6246, over 5733.00 frames. ], tot_loss[loss=3.673, NarTop10Accuracy=0.5903, over 6024.17 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (3/8) Epoch 5, batch 2400, train_loss[loss=3.377, NarTop10Accuracy=0.6504, over 5673.00 frames. ], tot_loss[loss=3.646, NarTop10Accuracy=0.596, over 5762.78 frames. ], batch size: 8, lr: 1.53e-02
2024-08-06 15:30:52,503 INFO [trainer.py:765] (3/8) Epoch 5, batch 2500, train_loss[loss=3.301, NarTop10Accuracy=0.6677, over 5748.00 frames. ], tot_loss[loss=3.606, NarTop10Accuracy=0.604, over 5470.41 frames. ], batch size: 8, lr: 1.52e-02
2024-08-06 15:31:12,345 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 15:32:14,415 INFO [trainer.py:765] (3/8) Epoch 6, batch 100, train_loss[loss=3.536, NarTop10Accuracy=0.6138, over 7356.00 frames. ], tot_loss[loss=3.637, NarTop10Accuracy=0.597, over 2367.77 frames. ], batch size: 33, lr: 1.42e-02
2024-08-06 15:32:46,015 INFO [trainer.py:765] (3/8) Epoch 6, batch 200, train_loss[loss=3.957, NarTop10Accuracy=0.529, over 6876.00 frames. ], tot_loss[loss=3.612, NarTop10Accuracy=0.6013, over 3859.88 frames. ], batch size: 17, lr: 1.42e-02
2024-08-06 15:33:21,242 INFO [trainer.py:765] (3/8) Epoch 6, batch 300, train_loss[loss=3.4, NarTop10Accuracy=0.6509, over 7227.00 frames. ], tot_loss[loss=3.606, NarTop10Accuracy=0.6029, over 4659.27 frames. ], batch size: 23, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (3/8) Epoch 6, batch 400, train_loss[loss=3.486, NarTop10Accuracy=0.6243, over 5118.00 frames. ], tot_loss[loss=3.592, NarTop10Accuracy=0.6066, over 5117.02 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (3/8) Epoch 6, batch 500, train_loss[loss=3.304, NarTop10Accuracy=0.6703, over 6087.00 frames. ], tot_loss[loss=3.577, NarTop10Accuracy=0.6098, over 5396.10 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,458 INFO [trainer.py:765] (3/8) Epoch 6, batch 600, train_loss[loss=3.256, NarTop10Accuracy=0.6787, over 5769.00 frames. ], tot_loss[loss=3.573, NarTop10Accuracy=0.6107, over 5653.44 frames. ], batch size: 9, lr: 1.40e-02
2024-08-06 15:35:32,734 INFO [trainer.py:765] (3/8) Epoch 6, batch 700, train_loss[loss=3.584, NarTop10Accuracy=0.6122, over 4965.00 frames. ], tot_loss[loss=3.579, NarTop10Accuracy=0.6095, over 5722.63 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (3/8) Epoch 6, batch 800, train_loss[loss=3.733, NarTop10Accuracy=0.5703, over 5019.00 frames. ], tot_loss[loss=3.592, NarTop10Accuracy=0.607, over 5783.36 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,384 INFO [trainer.py:765] (3/8) Epoch 6, batch 900, train_loss[loss=3.859, NarTop10Accuracy=0.5417, over 6630.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6089, over 5801.40 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:15,272 INFO [trainer.py:765] (3/8) Epoch 6, batch 1000, train_loss[loss=3.258, NarTop10Accuracy=0.6759, over 6102.00 frames. ], tot_loss[loss=3.596, NarTop10Accuracy=0.6059, over 5892.71 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (3/8) Epoch 6, batch 1100, train_loss[loss=3.389, NarTop10Accuracy=0.6497, over 6789.00 frames. ], tot_loss[loss=3.594, NarTop10Accuracy=0.6066, over 5935.83 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,828 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (3/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:38:04,965 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.415e+02 1.809e+02 1.991e+02 2.234e+02 5.215e+02, threshold=3.983e+02, percent-clipped=0.5
2024-08-06 15:38:36,168 INFO [trainer.py:765] (3/8) Epoch 6, batch 1200, train_loss[loss=3.366, NarTop10Accuracy=0.6539, over 7284.00 frames. ], tot_loss[loss=3.58, NarTop10Accuracy=0.6092, over 5938.35 frames. ], batch size: 31, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (3/8) Epoch 6, batch 1300, train_loss[loss=3.504, NarTop10Accuracy=0.6337, over 4341.00 frames. ], tot_loss[loss=3.58, NarTop10Accuracy=0.6094, over 5986.79 frames. ], batch size: 5, lr: 1.37e-02
2024-08-06 15:39:44,069 INFO [trainer.py:765] (3/8) Epoch 6, batch 1400, train_loss[loss=3.375, NarTop10Accuracy=0.6461, over 6165.00 frames. ], tot_loss[loss=3.577, NarTop10Accuracy=0.6102, over 6012.38 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (3/8) Epoch 6, batch 1500, train_loss[loss=3.958, NarTop10Accuracy=0.5224, over 6429.00 frames. ], tot_loss[loss=3.578, NarTop10Accuracy=0.6102, over 5961.06 frames. ], batch size: 50, lr: 1.36e-02
2024-08-06 15:40:43,105 INFO [trainer.py:765] (3/8) Epoch 6, batch 1600, train_loss[loss=3.437, NarTop10Accuracy=0.6469, over 7074.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6115, over 5930.66 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,788 INFO [trainer.py:765] (3/8) Epoch 6, batch 1700, train_loss[loss=3.457, NarTop10Accuracy=0.6316, over 6552.00 frames. ], tot_loss[loss=3.554, NarTop10Accuracy=0.6151, over 5918.90 frames. ], batch size: 14, lr: 1.35e-02
2024-08-06 15:41:36,316 INFO [trainer.py:765] (3/8) Epoch 6, batch 1800, train_loss[loss=3.519, NarTop10Accuracy=0.632, over 7005.00 frames. ], tot_loss[loss=3.56, NarTop10Accuracy=0.6134, over 5993.80 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (3/8) Epoch 6, batch 1900, train_loss[loss=3.82, NarTop10Accuracy=0.5688, over 6675.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6086, over 6031.57 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:28,318 INFO [trainer.py:765] (3/8) Epoch 6, batch 2000, train_loss[loss=3.498, NarTop10Accuracy=0.6231, over 6408.00 frames. ], tot_loss[loss=3.573, NarTop10Accuracy=0.6104, over 6010.00 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:53,668 INFO [trainer.py:765] (3/8) Epoch 6, batch 2100, train_loss[loss=3.3, NarTop10Accuracy=0.663, over 3879.00 frames. ], tot_loss[loss=3.565, NarTop10Accuracy=0.6121, over 5977.69 frames. ], batch size: 4, lr: 1.33e-02
2024-08-06 15:43:18,977 INFO [trainer.py:765] (3/8) Epoch 6, batch 2200, train_loss[loss=3.829, NarTop10Accuracy=0.5523, over 7341.00 frames. ], tot_loss[loss=3.566, NarTop10Accuracy=0.6118, over 6001.22 frames. ], batch size: 31, lr: 1.33e-02
2024-08-06 15:43:44,105 INFO [trainer.py:765] (3/8) Epoch 6, batch 2300, train_loss[loss=3.284, NarTop10Accuracy=0.6781, over 5808.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6108, over 6010.58 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (3/8) Epoch 6, batch 2400, train_loss[loss=3.299, NarTop10Accuracy=0.674, over 5241.00 frames. ], tot_loss[loss=3.536, NarTop10Accuracy=0.6177, over 5773.98 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (3/8) Epoch 6, batch 2500, train_loss[loss=3.434, NarTop10Accuracy=0.6409, over 4986.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.6203, over 5480.36 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:51,423 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 15:45:58,042 INFO [trainer.py:765] (3/8) Epoch 7, batch 100, train_loss[loss=3.315, NarTop10Accuracy=0.6608, over 7431.00 frames. ], tot_loss[loss=3.551, NarTop10Accuracy=0.6154, over 2365.13 frames. ], batch size: 32, lr: 1.24e-02
2024-08-06 15:46:33,614 INFO [trainer.py:765] (3/8) Epoch 7, batch 200, train_loss[loss=3.407, NarTop10Accuracy=0.6404, over 6828.00 frames. ], tot_loss[loss=3.528, NarTop10Accuracy=0.6198, over 3850.47 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,246 INFO [trainer.py:765] (3/8) Epoch 7, batch 300, train_loss[loss=3.771, NarTop10Accuracy=0.5812, over 7197.00 frames. ], tot_loss[loss=3.538, NarTop10Accuracy=0.6181, over 4645.37 frames. ], batch size: 23, lr: 1.23e-02
2024-08-06 15:47:34,495 INFO [trainer.py:765] (3/8) Epoch 7, batch 400, train_loss[loss=3.483, NarTop10Accuracy=0.6295, over 5718.00 frames. ], tot_loss[loss=3.529, NarTop10Accuracy=0.6196, over 5108.34 frames. ], batch size: 8, lr: 1.23e-02
2024-08-06 15:48:13,730 INFO [trainer.py:765] (3/8) Epoch 7, batch 500, train_loss[loss=3.72, NarTop10Accuracy=0.5827, over 6204.00 frames. ], tot_loss[loss=3.523, NarTop10Accuracy=0.6207, over 5405.49 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,368 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (3/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:48:35,078 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.466e+02 1.860e+02 2.018e+02 2.241e+02 5.111e+02, threshold=4.035e+02, percent-clipped=0.3
2024-08-06 15:48:52,720 INFO [trainer.py:765] (3/8) Epoch 7, batch 600, train_loss[loss=3.208, NarTop10Accuracy=0.6904, over 6204.00 frames. ], tot_loss[loss=3.532, NarTop10Accuracy=0.6187, over 5656.61 frames. ], batch size: 10, lr: 1.22e-02
2024-08-06 15:49:24,912 INFO [trainer.py:765] (3/8) Epoch 7, batch 700, train_loss[loss=3.741, NarTop10Accuracy=0.5769, over 5136.00 frames. ], tot_loss[loss=3.521, NarTop10Accuracy=0.6208, over 5728.78 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,381 INFO [trainer.py:765] (3/8) Epoch 7, batch 800, train_loss[loss=3.253, NarTop10Accuracy=0.6882, over 5154.00 frames. ], tot_loss[loss=3.506, NarTop10Accuracy=0.6246, over 5766.34 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:34,548 INFO [trainer.py:765] (3/8) Epoch 7, batch 900, train_loss[loss=3.365, NarTop10Accuracy=0.6578, over 6237.00 frames. ], tot_loss[loss=3.497, NarTop10Accuracy=0.626, over 5777.16 frames. ], batch size: 13, lr: 1.21e-02
2024-08-06 15:51:07,155 INFO [trainer.py:765] (3/8) Epoch 7, batch 1000, train_loss[loss=3.307, NarTop10Accuracy=0.6665, over 6249.00 frames. ], tot_loss[loss=3.49, NarTop10Accuracy=0.6275, over 5886.78 frames. ], batch size: 13, lr: 1.20e-02
2024-08-06 15:51:51,758 INFO [trainer.py:765] (3/8) Epoch 7, batch 1100, train_loss[loss=3.299, NarTop10Accuracy=0.6701, over 6684.00 frames. ], tot_loss[loss=3.493, NarTop10Accuracy=0.6267, over 5936.77 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,699 INFO [trainer.py:765] (3/8) Epoch 7, batch 1200, train_loss[loss=3.256, NarTop10Accuracy=0.6797, over 7569.00 frames. ], tot_loss[loss=3.489, NarTop10Accuracy=0.6277, over 5937.92 frames. ], batch size: 32, lr: 1.20e-02
2024-08-06 15:52:52,007 INFO [trainer.py:765] (3/8) Epoch 7, batch 1300, train_loss[loss=3.508, NarTop10Accuracy=0.6224, over 4986.00 frames. ], tot_loss[loss=3.491, NarTop10Accuracy=0.627, over 5979.24 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,842 INFO [trainer.py:765] (3/8) Epoch 7, batch 1400, train_loss[loss=3.276, NarTop10Accuracy=0.6695, over 6024.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6262, over 6014.61 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,600 INFO [trainer.py:765] (3/8) Epoch 7, batch 1500, train_loss[loss=3.771, NarTop10Accuracy=0.575, over 6138.00 frames. ], tot_loss[loss=3.475, NarTop10Accuracy=0.6306, over 5947.98 frames. ], batch size: 51, lr: 1.19e-02
2024-08-06 15:54:32,385 INFO [trainer.py:765] (3/8) Epoch 7, batch 1600, train_loss[loss=3.688, NarTop10Accuracy=0.5857, over 7206.00 frames. ], tot_loss[loss=3.479, NarTop10Accuracy=0.6299, over 5944.81 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,054 INFO [trainer.py:765] (3/8) Epoch 7, batch 1700, train_loss[loss=3.606, NarTop10Accuracy=0.6024, over 6666.00 frames. ], tot_loss[loss=3.493, NarTop10Accuracy=0.6266, over 5920.56 frames. ], batch size: 14, lr: 1.18e-02
2024-08-06 15:55:25,512 INFO [trainer.py:765] (3/8) Epoch 7, batch 1800, train_loss[loss=3.79, NarTop10Accuracy=0.5572, over 6972.00 frames. ], tot_loss[loss=3.489, NarTop10Accuracy=0.6273, over 5974.65 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,082 INFO [trainer.py:765] (3/8) Epoch 7, batch 1900, train_loss[loss=3.301, NarTop10Accuracy=0.6757, over 5790.00 frames. ], tot_loss[loss=3.506, NarTop10Accuracy=0.6242, over 6028.08 frames. ], batch size: 51, lr: 1.18e-02
2024-08-06 15:56:17,591 INFO [trainer.py:765] (3/8) Epoch 7, batch 2000, train_loss[loss=3.768, NarTop10Accuracy=0.5735, over 5889.00 frames. ], tot_loss[loss=3.503, NarTop10Accuracy=0.625, over 6002.24 frames. ], batch size: 51, lr: 1.17e-02
2024-08-06 15:56:42,856 INFO [trainer.py:765] (3/8) Epoch 7, batch 2100, train_loss[loss=3.534, NarTop10Accuracy=0.6019, over 3990.00 frames. ], tot_loss[loss=3.487, NarTop10Accuracy=0.6279, over 5986.06 frames. ], batch size: 4, lr: 1.17e-02
2024-08-06 15:57:08,079 INFO [trainer.py:765] (3/8) Epoch 7, batch 2200, train_loss[loss=3.468, NarTop10Accuracy=0.6323, over 7428.00 frames. ], tot_loss[loss=3.505, NarTop10Accuracy=0.6239, over 6022.60 frames. ], batch size: 32, lr: 1.17e-02
2024-08-06 15:57:33,178 INFO [trainer.py:765] (3/8) Epoch 7, batch 2300, train_loss[loss=3.286, NarTop10Accuracy=0.6741, over 5652.00 frames. ], tot_loss[loss=3.511, NarTop10Accuracy=0.6226, over 6024.86 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,619 INFO [trainer.py:765] (3/8) Epoch 7, batch 2400, train_loss[loss=3.182, NarTop10Accuracy=0.6873, over 5676.00 frames. ], tot_loss[loss=3.497, NarTop10Accuracy=0.6252, over 5777.56 frames. ], batch size: 8, lr: 1.16e-02
2024-08-06 15:58:21,088 INFO [trainer.py:765] (3/8) Epoch 7, batch 2500, train_loss[loss=3.558, NarTop10Accuracy=0.6079, over 5214.00 frames. ], tot_loss[loss=3.47, NarTop10Accuracy=0.6307, over 5477.75 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,565 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (3/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 15:58:40,220 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.471e+02 1.831e+02 1.996e+02 2.207e+02 5.229e+02, threshold=3.992e+02, percent-clipped=0.2
2024-08-06 15:58:48,981 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 15:59:52,877 INFO [trainer.py:765] (3/8) Epoch 8, batch 100, train_loss[loss=3.567, NarTop10Accuracy=0.6137, over 7770.00 frames. ], tot_loss[loss=3.452, NarTop10Accuracy=0.635, over 2363.54 frames. ], batch size: 33, lr: 1.09e-02
2024-08-06 16:00:27,881 INFO [trainer.py:765] (3/8) Epoch 8, batch 200, train_loss[loss=3.252, NarTop10Accuracy=0.6774, over 6963.00 frames. ], tot_loss[loss=3.473, NarTop10Accuracy=0.6299, over 3851.65 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,563 INFO [trainer.py:765] (3/8) Epoch 8, batch 300, train_loss[loss=3.289, NarTop10Accuracy=0.6712, over 7062.00 frames. ], tot_loss[loss=3.474, NarTop10Accuracy=0.6302, over 4670.11 frames. ], batch size: 22, lr: 1.08e-02
2024-08-06 16:01:29,760 INFO [trainer.py:765] (3/8) Epoch 8, batch 400, train_loss[loss=3.743, NarTop10Accuracy=0.5739, over 5013.00 frames. ], tot_loss[loss=3.477, NarTop10Accuracy=0.63, over 5107.33 frames. ], batch size: 7, lr: 1.08e-02
2024-08-06 16:02:04,066 INFO [trainer.py:765] (3/8) Epoch 8, batch 500, train_loss[loss=3.648, NarTop10Accuracy=0.5928, over 6147.00 frames. ], tot_loss[loss=3.454, NarTop10Accuracy=0.6345, over 5402.94 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,836 INFO [trainer.py:765] (3/8) Epoch 8, batch 600, train_loss[loss=3.08, NarTop10Accuracy=0.7081, over 5673.00 frames. ], tot_loss[loss=3.465, NarTop10Accuracy=0.6316, over 5655.59 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,501 INFO [trainer.py:765] (3/8) Epoch 8, batch 700, train_loss[loss=3.725, NarTop10Accuracy=0.576, over 5100.00 frames. ], tot_loss[loss=3.47, NarTop10Accuracy=0.6308, over 5726.17 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:03:50,084 INFO [trainer.py:765] (3/8) Epoch 8, batch 800, train_loss[loss=3.509, NarTop10Accuracy=0.6257, over 5061.00 frames. ], tot_loss[loss=3.462, NarTop10Accuracy=0.6326, over 5779.25 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:04:27,588 INFO [trainer.py:765] (3/8) Epoch 8, batch 900, train_loss[loss=3.082, NarTop10Accuracy=0.7136, over 6156.00 frames. ], tot_loss[loss=3.444, NarTop10Accuracy=0.6368, over 5796.42 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:04:57,466 INFO [trainer.py:765] (3/8) Epoch 8, batch 1000, train_loss[loss=3.608, NarTop10Accuracy=0.6034, over 6129.00 frames. ], tot_loss[loss=3.441, NarTop10Accuracy=0.6373, over 5914.58 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:05:37,294 INFO [trainer.py:765] (3/8) Epoch 8, batch 1100, train_loss[loss=3.664, NarTop10Accuracy=0.5854, over 6783.00 frames. ], tot_loss[loss=3.444, NarTop10Accuracy=0.6369, over 5934.10 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,859 INFO [trainer.py:765] (3/8) Epoch 8, batch 1200, train_loss[loss=3.432, NarTop10Accuracy=0.6429, over 7140.00 frames. ], tot_loss[loss=3.453, NarTop10Accuracy=0.6349, over 5924.61 frames. ], batch size: 31, lr: 1.06e-02
2024-08-06 16:06:45,187 INFO [trainer.py:765] (3/8) Epoch 8, batch 1300, train_loss[loss=3.126, NarTop10Accuracy=0.7107, over 4215.00 frames. ], tot_loss[loss=3.431, NarTop10Accuracy=0.6391, over 5981.40 frames. ], batch size: 5, lr: 1.06e-02
2024-08-06 16:07:24,236 INFO [trainer.py:765] (3/8) Epoch 8, batch 1400, train_loss[loss=3.508, NarTop10Accuracy=0.6232, over 5988.00 frames. ], tot_loss[loss=3.431, NarTop10Accuracy=0.6391, over 6015.17 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,169 INFO [trainer.py:765] (3/8) Epoch 8, batch 1500, train_loss[loss=3.42, NarTop10Accuracy=0.6447, over 6381.00 frames. ], tot_loss[loss=3.418, NarTop10Accuracy=0.642, over 5951.09 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,948 INFO [trainer.py:765] (3/8) Epoch 8, batch 1600, train_loss[loss=3.144, NarTop10Accuracy=0.7015, over 7098.00 frames. ], tot_loss[loss=3.417, NarTop10Accuracy=0.642, over 5932.41 frames. ], batch size: 22, lr: 1.05e-02
2024-08-06 16:08:46,618 INFO [trainer.py:765] (3/8) Epoch 8, batch 1700, train_loss[loss=3.358, NarTop10Accuracy=0.6517, over 6687.00 frames. ], tot_loss[loss=3.424, NarTop10Accuracy=0.6412, over 5908.61 frames. ], batch size: 14, lr: 1.05e-02
2024-08-06 16:09:13,106 INFO [trainer.py:765] (3/8) Epoch 8, batch 1800, train_loss[loss=3.264, NarTop10Accuracy=0.6768, over 7104.00 frames. ], tot_loss[loss=3.417, NarTop10Accuracy=0.6423, over 5971.38 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,636 INFO [trainer.py:765] (3/8) Epoch 8, batch 1900, train_loss[loss=3.744, NarTop10Accuracy=0.5803, over 6087.00 frames. ], tot_loss[loss=3.411, NarTop10Accuracy=0.6436, over 6021.73 frames. ], batch size: 51, lr: 1.04e-02
2024-08-06 16:09:56,940 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (3/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 16:10:05,470 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.411e+02 1.814e+02 1.981e+02 2.158e+02 5.862e+02, threshold=3.962e+02, percent-clipped=0.1
2024-08-06 16:10:13,204 INFO [trainer.py:765] (3/8) Epoch 8, batch 2000, train_loss[loss=3.948, NarTop10Accuracy=0.526, over 6420.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.6413, over 5999.04 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:10:38,514 INFO [trainer.py:765] (3/8) Epoch 8, batch 2100, train_loss[loss=3.545, NarTop10Accuracy=0.6193, over 3855.00 frames. ], tot_loss[loss=3.413, NarTop10Accuracy=0.6429, over 5991.74 frames. ], batch size: 4, lr: 1.04e-02
2024-08-06 16:11:03,747 INFO [trainer.py:765] (3/8) Epoch 8, batch 2200, train_loss[loss=3.536, NarTop10Accuracy=0.619, over 7182.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6405, over 6017.82 frames. ], batch size: 32, lr: 1.04e-02
2024-08-06 16:11:28,904 INFO [trainer.py:765] (3/8) Epoch 8, batch 2300, train_loss[loss=3.782, NarTop10Accuracy=0.5616, over 5787.00 frames. ], tot_loss[loss=3.447, NarTop10Accuracy=0.6364, over 6026.79 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,093 INFO [trainer.py:765] (3/8) Epoch 8, batch 2400, train_loss[loss=3.423, NarTop10Accuracy=0.6344, over 5136.00 frames. ], tot_loss[loss=3.429, NarTop10Accuracy=0.6397, over 5782.30 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:16,444 INFO [trainer.py:765] (3/8) Epoch 8, batch 2500, train_loss[loss=3.182, NarTop10Accuracy=0.6926, over 5040.00 frames. ], tot_loss[loss=3.409, NarTop10Accuracy=0.643, over 5474.87 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:36,672 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 16:13:37,514 INFO [trainer.py:765] (3/8) Epoch 9, batch 100, train_loss[loss=3.294, NarTop10Accuracy=0.6718, over 7149.00 frames. ], tot_loss[loss=3.361, NarTop10Accuracy=0.6546, over 2389.95 frames. ], batch size: 31, lr: 9.72e-03
2024-08-06 16:14:14,440 INFO [trainer.py:765] (3/8) Epoch 9, batch 200, train_loss[loss=3.656, NarTop10Accuracy=0.5967, over 6867.00 frames. ], tot_loss[loss=3.368, NarTop10Accuracy=0.653, over 3883.63 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,507 INFO [trainer.py:765] (3/8) Epoch 9, batch 300, train_loss[loss=3.353, NarTop10Accuracy=0.6584, over 7422.00 frames. ], tot_loss[loss=3.379, NarTop10Accuracy=0.65, over 4668.78 frames. ], batch size: 22, lr: 9.68e-03
2024-08-06 16:15:14,914 INFO [trainer.py:765] (3/8) Epoch 9, batch 400, train_loss[loss=3.129, NarTop10Accuracy=0.7043, over 5718.00 frames. ], tot_loss[loss=3.365, NarTop10Accuracy=0.653, over 5112.91 frames. ], batch size: 8, lr: 9.65e-03
2024-08-06 16:15:50,336 INFO [trainer.py:765] (3/8) Epoch 9, batch 500, train_loss[loss=3.215, NarTop10Accuracy=0.6947, over 6189.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6559, over 5397.23 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,972 INFO [trainer.py:765] (3/8) Epoch 9, batch 600, train_loss[loss=3.623, NarTop10Accuracy=0.6005, over 5637.00 frames. ], tot_loss[loss=3.342, NarTop10Accuracy=0.658, over 5664.19 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,145 INFO [trainer.py:765] (3/8) Epoch 9, batch 700, train_loss[loss=3.085, NarTop10Accuracy=0.705, over 5130.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.6549, over 5731.10 frames. ], batch size: 6, lr: 9.59e-03
2024-08-06 16:17:32,052 INFO [trainer.py:765] (3/8) Epoch 9, batch 800, train_loss[loss=3.229, NarTop10Accuracy=0.6825, over 4290.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.648, over 5792.51 frames. ], batch size: 5, lr: 9.57e-03
2024-08-06 16:18:07,815 INFO [trainer.py:765] (3/8) Epoch 9, batch 900, train_loss[loss=3.078, NarTop10Accuracy=0.7175, over 6189.00 frames. ], tot_loss[loss=3.383, NarTop10Accuracy=0.6491, over 5797.15 frames. ], batch size: 13, lr: 9.55e-03
2024-08-06 16:18:39,344 INFO [trainer.py:765] (3/8) Epoch 9, batch 1000, train_loss[loss=3.13, NarTop10Accuracy=0.6868, over 6264.00 frames. ], tot_loss[loss=3.398, NarTop10Accuracy=0.6462, over 5890.54 frames. ], batch size: 13, lr: 9.53e-03
2024-08-06 16:19:15,382 INFO [trainer.py:765] (3/8) Epoch 9, batch 1100, train_loss[loss=3.408, NarTop10Accuracy=0.6392, over 6876.00 frames. ], tot_loss[loss=3.399, NarTop10Accuracy=0.6456, over 5922.72 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,877 INFO [trainer.py:765] (3/8) Epoch 9, batch 1200, train_loss[loss=3.882, NarTop10Accuracy=0.5438, over 7029.00 frames. ], tot_loss[loss=3.403, NarTop10Accuracy=0.6448, over 5918.43 frames. ], batch size: 31, lr: 9.48e-03
2024-08-06 16:20:24,906 INFO [trainer.py:765] (3/8) Epoch 9, batch 1300, train_loss[loss=3.192, NarTop10Accuracy=0.6912, over 5226.00 frames. ], tot_loss[loss=3.399, NarTop10Accuracy=0.6458, over 5989.98 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,578 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (3/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.473e+02 1.808e+02 1.967e+02 2.142e+02 6.126e+02, threshold=3.935e+02, percent-clipped=0.5
2024-08-06 16:21:06,690 INFO [trainer.py:765] (3/8) Epoch 9, batch 1400, train_loss[loss=3.451, NarTop10Accuracy=0.6322, over 6039.00 frames. ], tot_loss[loss=3.408, NarTop10Accuracy=0.6441, over 6021.73 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,895 INFO [trainer.py:765] (3/8) Epoch 9, batch 1500, train_loss[loss=3.439, NarTop10Accuracy=0.6385, over 6000.00 frames. ], tot_loss[loss=3.387, NarTop10Accuracy=0.6486, over 5961.47 frames. ], batch size: 51, lr: 9.42e-03
2024-08-06 16:22:06,720 INFO [trainer.py:765] (3/8) Epoch 9, batch 1600, train_loss[loss=3.342, NarTop10Accuracy=0.6617, over 7095.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6509, over 5951.18 frames. ], batch size: 22, lr: 9.40e-03
2024-08-06 16:22:33,470 INFO [trainer.py:765] (3/8) Epoch 9, batch 1700, train_loss[loss=3.529, NarTop10Accuracy=0.6182, over 6498.00 frames. ], tot_loss[loss=3.39, NarTop10Accuracy=0.6477, over 5929.96 frames. ], batch size: 14, lr: 9.38e-03
2024-08-06 16:23:00,062 INFO [trainer.py:765] (3/8) Epoch 9, batch 1800, train_loss[loss=3.309, NarTop10Accuracy=0.6747, over 7266.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6493, over 5986.67 frames. ], batch size: 23, lr: 9.36e-03
2024-08-06 16:23:26,783 INFO [trainer.py:765] (3/8) Epoch 9, batch 1900, train_loss[loss=3.439, NarTop10Accuracy=0.6415, over 6267.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6472, over 6024.04 frames. ], batch size: 50, lr: 9.34e-03
2024-08-06 16:23:52,485 INFO [trainer.py:765] (3/8) Epoch 9, batch 2000, train_loss[loss=3.87, NarTop10Accuracy=0.5464, over 6993.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6487, over 6001.50 frames. ], batch size: 52, lr: 9.32e-03
2024-08-06 16:24:17,962 INFO [trainer.py:765] (3/8) Epoch 9, batch 2100, train_loss[loss=3.228, NarTop10Accuracy=0.6802, over 4887.00 frames. ], tot_loss[loss=3.381, NarTop10Accuracy=0.6485, over 5986.43 frames. ], batch size: 5, lr: 9.30e-03
2024-08-06 16:24:43,421 INFO [trainer.py:765] (3/8) Epoch 9, batch 2200, train_loss[loss=3.689, NarTop10Accuracy=0.5827, over 7605.00 frames. ], tot_loss[loss=3.392, NarTop10Accuracy=0.647, over 6020.48 frames. ], batch size: 32, lr: 9.28e-03
2024-08-06 16:25:08,721 INFO [trainer.py:765] (3/8) Epoch 9, batch 2300, train_loss[loss=3.202, NarTop10Accuracy=0.6892, over 5685.00 frames. ], tot_loss[loss=3.406, NarTop10Accuracy=0.6439, over 6032.70 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,162 INFO [trainer.py:765] (3/8) Epoch 9, batch 2400, train_loss[loss=3.292, NarTop10Accuracy=0.667, over 4974.00 frames. ], tot_loss[loss=3.403, NarTop10Accuracy=0.6441, over 5765.77 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,767 INFO [trainer.py:765] (3/8) Epoch 9, batch 2500, train_loss[loss=3.39, NarTop10Accuracy=0.6469, over 5277.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6498, over 5465.34 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,370 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 16:27:19,584 INFO [trainer.py:765] (3/8) Epoch 10, batch 100, train_loss[loss=3.288, NarTop10Accuracy=0.6686, over 7152.00 frames. ], tot_loss[loss=3.38, NarTop10Accuracy=0.6508, over 2349.70 frames. ], batch size: 31, lr: 8.76e-03
2024-08-06 16:27:52,628 INFO [trainer.py:765] (3/8) Epoch 10, batch 200, train_loss[loss=3.005, NarTop10Accuracy=0.7301, over 6789.00 frames. ], tot_loss[loss=3.362, NarTop10Accuracy=0.6537, over 3846.63 frames. ], batch size: 17, lr: 8.74e-03
2024-08-06 16:28:23,057 INFO [trainer.py:765] (3/8) Epoch 10, batch 300, train_loss[loss=3.058, NarTop10Accuracy=0.7225, over 7008.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.655, over 4662.18 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,200 INFO [trainer.py:765] (3/8) Epoch 10, batch 400, train_loss[loss=3.357, NarTop10Accuracy=0.6599, over 5091.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6573, over 5118.78 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,218 INFO [trainer.py:765] (3/8) Epoch 10, batch 500, train_loss[loss=3.063, NarTop10Accuracy=0.7125, over 6165.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6581, over 5390.58 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,765 INFO [trainer.py:765] (3/8) Epoch 10, batch 600, train_loss[loss=3.334, NarTop10Accuracy=0.6556, over 5745.00 frames. ], tot_loss[loss=3.342, NarTop10Accuracy=0.6574, over 5635.93 frames. ], batch size: 9, lr: 8.67e-03
2024-08-06 16:30:34,265 INFO [trainer.py:765] (3/8) Epoch 10, batch 700, train_loss[loss=3.246, NarTop10Accuracy=0.6632, over 5094.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6564, over 5721.05 frames. ], batch size: 6, lr: 8.65e-03
2024-08-06 16:31:09,843 INFO [trainer.py:765] (3/8) Epoch 10, batch 800, train_loss[loss=3.632, NarTop10Accuracy=0.5945, over 4368.00 frames. ], tot_loss[loss=3.354, NarTop10Accuracy=0.6548, over 5770.70 frames. ], batch size: 5, lr: 8.64e-03
2024-08-06 16:31:16,258 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (3/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,566 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.434e+02 1.851e+02 2.012e+02 2.196e+02 4.599e+02, threshold=4.024e+02, percent-clipped=0.1
2024-08-06 16:31:50,345 INFO [trainer.py:765] (3/8) Epoch 10, batch 900, train_loss[loss=3.264, NarTop10Accuracy=0.6671, over 6804.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6598, over 5810.36 frames. ], batch size: 14, lr: 8.62e-03
2024-08-06 16:32:28,588 INFO [trainer.py:765] (3/8) Epoch 10, batch 1000, train_loss[loss=3.186, NarTop10Accuracy=0.6922, over 6147.00 frames. ], tot_loss[loss=3.336, NarTop10Accuracy=0.6584, over 5905.94 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,376 INFO [trainer.py:765] (3/8) Epoch 10, batch 1100, train_loss[loss=3.144, NarTop10Accuracy=0.7023, over 6738.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.656, over 5930.28 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,960 INFO [trainer.py:765] (3/8) Epoch 10, batch 1200, train_loss[loss=3.231, NarTop10Accuracy=0.6823, over 7398.00 frames. ], tot_loss[loss=3.334, NarTop10Accuracy=0.6584, over 5931.91 frames. ], batch size: 31, lr: 8.57e-03
2024-08-06 16:34:16,169 INFO [trainer.py:765] (3/8) Epoch 10, batch 1300, train_loss[loss=3.369, NarTop10Accuracy=0.6495, over 5019.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6584, over 5998.08 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,200 INFO [trainer.py:765] (3/8) Epoch 10, batch 1400, train_loss[loss=3.33, NarTop10Accuracy=0.6541, over 6105.00 frames. ], tot_loss[loss=3.359, NarTop10Accuracy=0.6531, over 6005.02 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,159 INFO [trainer.py:765] (3/8) Epoch 10, batch 1500, train_loss[loss=3.588, NarTop10Accuracy=0.6113, over 5946.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6575, over 5936.48 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (3/8) Epoch 10, batch 1600, train_loss[loss=3.679, NarTop10Accuracy=0.5875, over 6738.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6597, over 5927.21 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,976 INFO [trainer.py:765] (3/8) Epoch 10, batch 1700, train_loss[loss=3.404, NarTop10Accuracy=0.6423, over 6573.00 frames. ], tot_loss[loss=3.342, NarTop10Accuracy=0.6573, over 5933.10 frames. ], batch size: 14, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (3/8) Epoch 10, batch 1800, train_loss[loss=3.232, NarTop10Accuracy=0.6694, over 7050.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6594, over 6004.90 frames. ], batch size: 22, lr: 8.47e-03
2024-08-06 16:37:10,290 INFO [trainer.py:765] (3/8) Epoch 10, batch 1900, train_loss[loss=3.289, NarTop10Accuracy=0.6802, over 6636.00 frames. ], tot_loss[loss=3.334, NarTop10Accuracy=0.6589, over 6055.32 frames. ], batch size: 51, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (3/8) Epoch 10, batch 2000, train_loss[loss=3.304, NarTop10Accuracy=0.6765, over 6183.00 frames. ], tot_loss[loss=3.328, NarTop10Accuracy=0.6606, over 6019.86 frames. ], batch size: 50, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (3/8) Epoch 10, batch 2100, train_loss[loss=3.473, NarTop10Accuracy=0.6356, over 3828.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6575, over 5977.12 frames. ], batch size: 4, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (3/8) Epoch 10, batch 2200, train_loss[loss=3.809, NarTop10Accuracy=0.5423, over 7014.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6564, over 6023.36 frames. ], batch size: 31, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (3/8) Epoch 10, batch 2300, train_loss[loss=3.079, NarTop10Accuracy=0.7077, over 5775.00 frames. ], tot_loss[loss=3.35, NarTop10Accuracy=0.6559, over 6042.92 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,005 INFO [trainer.py:765] (3/8) Epoch 10, batch 2400, train_loss[loss=3.116, NarTop10Accuracy=0.7013, over 5094.00 frames. ], tot_loss[loss=3.323, NarTop10Accuracy=0.6613, over 5789.73 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (3/8) Epoch 10, batch 2500, train_loss[loss=3.724, NarTop10Accuracy=0.5749, over 5106.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6662, over 5505.50 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,807 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 16:41:06,235 INFO [trainer.py:765] (3/8) Epoch 11, batch 100, train_loss[loss=3.664, NarTop10Accuracy=0.5944, over 7383.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6562, over 2358.08 frames. ], batch size: 31, lr: 7.97e-03
2024-08-06 16:41:39,021 INFO [trainer.py:765] (3/8) Epoch 11, batch 200, train_loss[loss=3.59, NarTop10Accuracy=0.6029, over 6864.00 frames. ], tot_loss[loss=3.328, NarTop10Accuracy=0.6601, over 3866.81 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,191 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (3/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.526e+02 1.889e+02 2.046e+02 2.249e+02 5.417e+02, threshold=4.093e+02, percent-clipped=0.2
2024-08-06 16:42:17,976 INFO [trainer.py:765] (3/8) Epoch 11, batch 300, train_loss[loss=3.076, NarTop10Accuracy=0.7129, over 7023.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6664, over 4652.14 frames. ], batch size: 22, lr: 7.94e-03
2024-08-06 16:42:55,155 INFO [trainer.py:765] (3/8) Epoch 11, batch 400, train_loss[loss=3.334, NarTop10Accuracy=0.6619, over 5196.00 frames. ], tot_loss[loss=3.288, NarTop10Accuracy=0.6684, over 5096.07 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,719 INFO [trainer.py:765] (3/8) Epoch 11, batch 500, train_loss[loss=3.017, NarTop10Accuracy=0.7247, over 6171.00 frames. ], tot_loss[loss=3.284, NarTop10Accuracy=0.6694, over 5383.79 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,241 INFO [trainer.py:765] (3/8) Epoch 11, batch 600, train_loss[loss=3.476, NarTop10Accuracy=0.6294, over 5679.00 frames. ], tot_loss[loss=3.296, NarTop10Accuracy=0.6669, over 5648.76 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,716 INFO [trainer.py:765] (3/8) Epoch 11, batch 700, train_loss[loss=3.562, NarTop10Accuracy=0.6113, over 4305.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6683, over 5728.43 frames. ], batch size: 5, lr: 7.88e-03
2024-08-06 16:45:10,468 INFO [trainer.py:765] (3/8) Epoch 11, batch 800, train_loss[loss=3.067, NarTop10Accuracy=0.7145, over 4260.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6641, over 5783.97 frames. ], batch size: 5, lr: 7.86e-03
2024-08-06 16:45:46,458 INFO [trainer.py:765] (3/8) Epoch 11, batch 900, train_loss[loss=3.758, NarTop10Accuracy=0.5715, over 6693.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6637, over 5806.25 frames. ], batch size: 14, lr: 7.85e-03
2024-08-06 16:46:20,311 INFO [trainer.py:765] (3/8) Epoch 11, batch 1000, train_loss[loss=3.342, NarTop10Accuracy=0.6481, over 6624.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6638, over 5901.06 frames. ], batch size: 14, lr: 7.84e-03
2024-08-06 16:46:53,457 INFO [trainer.py:765] (3/8) Epoch 11, batch 1100, train_loss[loss=2.962, NarTop10Accuracy=0.7335, over 6786.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6653, over 5961.03 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (3/8) Epoch 11, batch 1200, train_loss[loss=3.477, NarTop10Accuracy=0.6288, over 7095.00 frames. ], tot_loss[loss=3.309, NarTop10Accuracy=0.6641, over 5955.19 frames. ], batch size: 31, lr: 7.81e-03
2024-08-06 16:48:06,482 INFO [trainer.py:765] (3/8) Epoch 11, batch 1300, train_loss[loss=2.947, NarTop10Accuracy=0.7535, over 5058.00 frames. ], tot_loss[loss=3.309, NarTop10Accuracy=0.6637, over 6003.43 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,355 INFO [trainer.py:765] (3/8) Epoch 11, batch 1400, train_loss[loss=3.523, NarTop10Accuracy=0.6217, over 6012.00 frames. ], tot_loss[loss=3.328, NarTop10Accuracy=0.66, over 6012.38 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,345 INFO [trainer.py:765] (3/8) Epoch 11, batch 1500, train_loss[loss=3.302, NarTop10Accuracy=0.6732, over 5823.00 frames. ], tot_loss[loss=3.334, NarTop10Accuracy=0.6587, over 5955.35 frames. ], batch size: 51, lr: 7.77e-03
2024-08-06 16:49:37,103 INFO [trainer.py:765] (3/8) Epoch 11, batch 1600, train_loss[loss=3.21, NarTop10Accuracy=0.6852, over 7062.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.6627, over 5937.41 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,792 INFO [trainer.py:765] (3/8) Epoch 11, batch 1700, train_loss[loss=3.441, NarTop10Accuracy=0.635, over 6600.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6648, over 5902.46 frames. ], batch size: 14, lr: 7.74e-03
2024-08-06 16:50:30,354 INFO [trainer.py:765] (3/8) Epoch 11, batch 1800, train_loss[loss=3.532, NarTop10Accuracy=0.6197, over 6996.00 frames. ], tot_loss[loss=3.325, NarTop10Accuracy=0.6609, over 5984.99 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,822 INFO [trainer.py:765] (3/8) Epoch 11, batch 1900, train_loss[loss=3.781, NarTop10Accuracy=0.564, over 5646.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6599, over 6015.26 frames. ], batch size: 50, lr: 7.71e-03
2024-08-06 16:51:22,405 INFO [trainer.py:765] (3/8) Epoch 11, batch 2000, train_loss[loss=3.86, NarTop10Accuracy=0.5464, over 6060.00 frames. ], tot_loss[loss=3.312, NarTop10Accuracy=0.663, over 5998.13 frames. ], batch size: 50, lr: 7.70e-03
2024-08-06 16:51:47,794 INFO [trainer.py:765] (3/8) Epoch 11, batch 2100, train_loss[loss=3.078, NarTop10Accuracy=0.7182, over 4812.00 frames. ], tot_loss[loss=3.308, NarTop10Accuracy=0.6641, over 5984.94 frames. ], batch size: 5, lr: 7.68e-03
2024-08-06 16:52:13,118 INFO [trainer.py:765] (3/8) Epoch 11, batch 2200, train_loss[loss=3.344, NarTop10Accuracy=0.6573, over 7371.00 frames. ], tot_loss[loss=3.308, NarTop10Accuracy=0.6642, over 6017.26 frames. ], batch size: 31, lr: 7.67e-03
2024-08-06 16:52:23,899 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (3/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,080 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.491e+02 1.920e+02 2.088e+02 2.244e+02 3.599e+02, threshold=4.177e+02, percent-clipped=0.0
2024-08-06 16:52:46,444 INFO [trainer.py:765] (3/8) Epoch 11, batch 2300, train_loss[loss=3.14, NarTop10Accuracy=0.702, over 5553.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.6627, over 6013.65 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (3/8) Epoch 11, batch 2400, train_loss[loss=3.594, NarTop10Accuracy=0.6113, over 5754.00 frames. ], tot_loss[loss=3.308, NarTop10Accuracy=0.6643, over 5782.15 frames. ], batch size: 8, lr: 7.64e-03
2024-08-06 16:53:34,371 INFO [trainer.py:765] (3/8) Epoch 11, batch 2500, train_loss[loss=3.523, NarTop10Accuracy=0.616, over 5169.00 frames. ], tot_loss[loss=3.296, NarTop10Accuracy=0.666, over 5483.88 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,339 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 16:54:58,525 INFO [trainer.py:765] (3/8) Epoch 12, batch 100, train_loss[loss=3.708, NarTop10Accuracy=0.5796, over 6987.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6649, over 2363.90 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,432 INFO [trainer.py:765] (3/8) Epoch 12, batch 200, train_loss[loss=3.225, NarTop10Accuracy=0.6877, over 6783.00 frames. ], tot_loss[loss=3.278, NarTop10Accuracy=0.6704, over 3852.95 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,096 INFO [trainer.py:765] (3/8) Epoch 12, batch 300, train_loss[loss=3.034, NarTop10Accuracy=0.7167, over 7185.00 frames. ], tot_loss[loss=3.249, NarTop10Accuracy=0.6765, over 4648.02 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,426 INFO [trainer.py:765] (3/8) Epoch 12, batch 400, train_loss[loss=3.062, NarTop10Accuracy=0.716, over 5103.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6743, over 5121.65 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,503 INFO [trainer.py:765] (3/8) Epoch 12, batch 500, train_loss[loss=3.548, NarTop10Accuracy=0.6021, over 6144.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6728, over 5385.65 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,483 INFO [trainer.py:765] (3/8) Epoch 12, batch 600, train_loss[loss=2.931, NarTop10Accuracy=0.738, over 5598.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.6732, over 5655.20 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,005 INFO [trainer.py:765] (3/8) Epoch 12, batch 700, train_loss[loss=3.682, NarTop10Accuracy=0.5821, over 4365.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6695, over 5707.25 frames. ], batch size: 5, lr: 7.22e-03
2024-08-06 16:58:53,469 INFO [trainer.py:765] (3/8) Epoch 12, batch 800, train_loss[loss=3.279, NarTop10Accuracy=0.6683, over 5058.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.6678, over 5768.66 frames. ], batch size: 6, lr: 7.21e-03
2024-08-06 16:59:27,206 INFO [trainer.py:765] (3/8) Epoch 12, batch 900, train_loss[loss=3.068, NarTop10Accuracy=0.7167, over 6129.00 frames. ], tot_loss[loss=3.274, NarTop10Accuracy=0.6714, over 5801.80 frames. ], batch size: 13, lr: 7.20e-03
2024-08-06 17:00:01,574 INFO [trainer.py:765] (3/8) Epoch 12, batch 1000, train_loss[loss=3.075, NarTop10Accuracy=0.7164, over 6243.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.668, over 5912.82 frames. ], batch size: 13, lr: 7.19e-03
2024-08-06 17:00:39,189 INFO [trainer.py:765] (3/8) Epoch 12, batch 1100, train_loss[loss=3.626, NarTop10Accuracy=0.5937, over 6777.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6647, over 5933.28 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,963 INFO [trainer.py:765] (3/8) Epoch 12, batch 1200, train_loss[loss=3.017, NarTop10Accuracy=0.7267, over 7407.00 frames. ], tot_loss[loss=3.268, NarTop10Accuracy=0.6724, over 5921.54 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,107 INFO [trainer.py:765] (3/8) Epoch 12, batch 1300, train_loss[loss=3.198, NarTop10Accuracy=0.6873, over 5073.00 frames. ], tot_loss[loss=3.278, NarTop10Accuracy=0.6705, over 5993.79 frames. ], batch size: 6, lr: 7.15e-03
2024-08-06 17:02:22,323 INFO [trainer.py:765] (3/8) Epoch 12, batch 1400, train_loss[loss=3.591, NarTop10Accuracy=0.6051, over 6042.00 frames. ], tot_loss[loss=3.293, NarTop10Accuracy=0.6673, over 6014.00 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,877 INFO [trainer.py:765] (3/8) Epoch 12, batch 1500, train_loss[loss=3.438, NarTop10Accuracy=0.6484, over 5703.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6716, over 5953.85 frames. ], batch size: 51, lr: 7.13e-03
2024-08-06 17:03:20,691 INFO [trainer.py:765] (3/8) Epoch 12, batch 1600, train_loss[loss=3.311, NarTop10Accuracy=0.659, over 7089.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6686, over 5929.92 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,296 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:03:46,473 INFO [trainer.py:811] (3/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,474 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:03:46,987 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.507e+02 1.899e+02 2.078e+02 2.276e+02 5.455e+02, threshold=4.157e+02, percent-clipped=0.1
2024-08-06 17:03:55,601 INFO [trainer.py:765] (3/8) Epoch 12, batch 1700, train_loss[loss=3.426, NarTop10Accuracy=0.6359, over 6279.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.668, over 5914.92 frames. ], batch size: 13, lr: 7.11e-03
2024-08-06 17:04:22,119 INFO [trainer.py:765] (3/8) Epoch 12, batch 1800, train_loss[loss=3.61, NarTop10Accuracy=0.5964, over 7059.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6679, over 5970.26 frames. ], batch size: 22, lr: 7.10e-03
2024-08-06 17:04:48,589 INFO [trainer.py:765] (3/8) Epoch 12, batch 1900, train_loss[loss=3.306, NarTop10Accuracy=0.6728, over 5979.00 frames. ], tot_loss[loss=3.283, NarTop10Accuracy=0.6697, over 6013.03 frames. ], batch size: 50, lr: 7.08e-03
2024-08-06 17:05:14,196 INFO [trainer.py:765] (3/8) Epoch 12, batch 2000, train_loss[loss=3.531, NarTop10Accuracy=0.6126, over 6291.00 frames. ], tot_loss[loss=3.271, NarTop10Accuracy=0.6718, over 6000.16 frames. ], batch size: 51, lr: 7.07e-03
2024-08-06 17:05:39,466 INFO [trainer.py:765] (3/8) Epoch 12, batch 2100, train_loss[loss=3.351, NarTop10Accuracy=0.654, over 3981.00 frames. ], tot_loss[loss=3.274, NarTop10Accuracy=0.671, over 5975.26 frames. ], batch size: 4, lr: 7.06e-03
2024-08-06 17:06:04,689 INFO [trainer.py:765] (3/8) Epoch 12, batch 2200, train_loss[loss=3.38, NarTop10Accuracy=0.6464, over 7383.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.6676, over 6002.03 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,845 INFO [trainer.py:765] (3/8) Epoch 12, batch 2300, train_loss[loss=3.463, NarTop10Accuracy=0.625, over 5697.00 frames. ], tot_loss[loss=3.283, NarTop10Accuracy=0.669, over 6018.97 frames. ], batch size: 9, lr: 7.04e-03
2024-08-06 17:06:54,199 INFO [trainer.py:765] (3/8) Epoch 12, batch 2400, train_loss[loss=3.189, NarTop10Accuracy=0.6991, over 5244.00 frames. ], tot_loss[loss=3.274, NarTop10Accuracy=0.6705, over 5776.49 frames. ], batch size: 7, lr: 7.03e-03
2024-08-06 17:07:17,645 INFO [trainer.py:765] (3/8) Epoch 12, batch 2500, train_loss[loss=3.243, NarTop10Accuracy=0.6695, over 5091.00 frames. ], tot_loss[loss=3.26, NarTop10Accuracy=0.6734, over 5475.16 frames. ], batch size: 7, lr: 7.02e-03
2024-08-06 17:07:37,619 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 17:08:40,078 INFO [trainer.py:765] (3/8) Epoch 13, batch 100, train_loss[loss=3.175, NarTop10Accuracy=0.6911, over 7416.00 frames. ], tot_loss[loss=3.295, NarTop10Accuracy=0.6677, over 2368.03 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,119 INFO [trainer.py:765] (3/8) Epoch 13, batch 200, train_loss[loss=3.009, NarTop10Accuracy=0.7228, over 6798.00 frames. ], tot_loss[loss=3.284, NarTop10Accuracy=0.6702, over 3850.44 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,276 INFO [trainer.py:765] (3/8) Epoch 13, batch 300, train_loss[loss=3.53, NarTop10Accuracy=0.6159, over 7383.00 frames. ], tot_loss[loss=3.261, NarTop10Accuracy=0.6747, over 4667.72 frames. ], batch size: 23, lr: 6.71e-03
2024-08-06 17:10:19,163 INFO [trainer.py:765] (3/8) Epoch 13, batch 400, train_loss[loss=2.987, NarTop10Accuracy=0.7314, over 5031.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.6772, over 5128.25 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,335 INFO [trainer.py:765] (3/8) Epoch 13, batch 500, train_loss[loss=3.146, NarTop10Accuracy=0.6928, over 6054.00 frames. ], tot_loss[loss=3.243, NarTop10Accuracy=0.6779, over 5391.57 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,244 INFO [trainer.py:765] (3/8) Epoch 13, batch 600, train_loss[loss=3.091, NarTop10Accuracy=0.7093, over 5799.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6797, over 5647.50 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (3/8) Epoch 13, batch 700, train_loss[loss=3.078, NarTop10Accuracy=0.7094, over 5073.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6784, over 5725.00 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,441 INFO [trainer.py:765] (3/8) Epoch 13, batch 800, train_loss[loss=2.913, NarTop10Accuracy=0.7432, over 5124.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.6771, over 5792.55 frames. ], batch size: 6, lr: 6.66e-03
2024-08-06 17:13:10,032 INFO [trainer.py:765] (3/8) Epoch 13, batch 900, train_loss[loss=3.291, NarTop10Accuracy=0.6669, over 6174.00 frames. ], tot_loss[loss=3.241, NarTop10Accuracy=0.6779, over 5802.45 frames. ], batch size: 13, lr: 6.65e-03
2024-08-06 17:13:41,442 INFO [trainer.py:765] (3/8) Epoch 13, batch 1000, train_loss[loss=3.739, NarTop10Accuracy=0.5865, over 6273.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.6771, over 5900.22 frames. ], batch size: 13, lr: 6.64e-03
2024-08-06 17:14:15,536 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (3/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:14:24,471 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.548e+02 1.948e+02 2.091e+02 2.295e+02 3.353e+02, threshold=4.181e+02, percent-clipped=0.0
2024-08-06 17:14:26,697 INFO [trainer.py:765] (3/8) Epoch 13, batch 1100, train_loss[loss=3.439, NarTop10Accuracy=0.6339, over 6831.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6757, over 5936.46 frames. ], batch size: 17, lr: 6.63e-03
2024-08-06 17:15:03,476 INFO [trainer.py:765] (3/8) Epoch 13, batch 1200, train_loss[loss=3.398, NarTop10Accuracy=0.6408, over 7143.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6747, over 5920.43 frames. ], batch size: 31, lr: 6.62e-03
2024-08-06 17:15:35,514 INFO [trainer.py:765] (3/8) Epoch 13, batch 1300, train_loss[loss=2.953, NarTop10Accuracy=0.7445, over 5139.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6734, over 5991.28 frames. ], batch size: 6, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (3/8) Epoch 13, batch 1400, train_loss[loss=3.07, NarTop10Accuracy=0.7146, over 6153.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6736, over 6001.29 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,788 INFO [trainer.py:765] (3/8) Epoch 13, batch 1500, train_loss[loss=3.551, NarTop10Accuracy=0.6066, over 6213.00 frames. ], tot_loss[loss=3.262, NarTop10Accuracy=0.6736, over 5937.55 frames. ], batch size: 50, lr: 6.59e-03
2024-08-06 17:17:07,603 INFO [trainer.py:765] (3/8) Epoch 13, batch 1600, train_loss[loss=3.076, NarTop10Accuracy=0.7038, over 7125.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6727, over 5918.73 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,259 INFO [trainer.py:765] (3/8) Epoch 13, batch 1700, train_loss[loss=3.17, NarTop10Accuracy=0.6887, over 6198.00 frames. ], tot_loss[loss=3.26, NarTop10Accuracy=0.6735, over 5905.51 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,762 INFO [trainer.py:765] (3/8) Epoch 13, batch 1800, train_loss[loss=3.042, NarTop10Accuracy=0.7177, over 7263.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6756, over 5970.27 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,244 INFO [trainer.py:765] (3/8) Epoch 13, batch 1900, train_loss[loss=3.46, NarTop10Accuracy=0.633, over 5916.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6762, over 5997.16 frames. ], batch size: 50, lr: 6.55e-03
2024-08-06 17:18:52,778 INFO [trainer.py:765] (3/8) Epoch 13, batch 2000, train_loss[loss=3.508, NarTop10Accuracy=0.63, over 5937.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6794, over 5989.38 frames. ], batch size: 50, lr: 6.54e-03
2024-08-06 17:19:18,147 INFO [trainer.py:765] (3/8) Epoch 13, batch 2100, train_loss[loss=2.888, NarTop10Accuracy=0.7506, over 4878.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6805, over 5972.49 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,412 INFO [trainer.py:765] (3/8) Epoch 13, batch 2200, train_loss[loss=3.37, NarTop10Accuracy=0.6497, over 7275.00 frames. ], tot_loss[loss=3.241, NarTop10Accuracy=0.6783, over 6006.92 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,543 INFO [trainer.py:765] (3/8) Epoch 13, batch 2300, train_loss[loss=3.6, NarTop10Accuracy=0.6022, over 5682.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6728, over 6038.96 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,940 INFO [trainer.py:765] (3/8) Epoch 13, batch 2400, train_loss[loss=3.803, NarTop10Accuracy=0.5728, over 5145.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6793, over 5773.62 frames. ], batch size: 7, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (3/8) Epoch 13, batch 2500, train_loss[loss=3.584, NarTop10Accuracy=0.6113, over 5388.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6812, over 5456.46 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,306 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 17:22:19,315 INFO [trainer.py:765] (3/8) Epoch 14, batch 100, train_loss[loss=3.001, NarTop10Accuracy=0.7341, over 7185.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.6808, over 2382.05 frames. ], batch size: 32, lr: 6.24e-03
2024-08-06 17:22:50,378 INFO [trainer.py:765] (3/8) Epoch 14, batch 200, train_loss[loss=3.289, NarTop10Accuracy=0.6705, over 6840.00 frames. ], tot_loss[loss=3.234, NarTop10Accuracy=0.6795, over 3864.81 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,879 INFO [trainer.py:765] (3/8) Epoch 14, batch 300, train_loss[loss=3.141, NarTop10Accuracy=0.6969, over 6999.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6843, over 4673.83 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,484 INFO [trainer.py:765] (3/8) Epoch 14, batch 400, train_loss[loss=3.038, NarTop10Accuracy=0.719, over 5073.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6811, over 5132.64 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,113 INFO [trainer.py:765] (3/8) Epoch 14, batch 500, train_loss[loss=3.3, NarTop10Accuracy=0.6641, over 6042.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6785, over 5406.77 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,213 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (3/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,276 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:24:44,823 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.601e+02 1.969e+02 2.114e+02 2.287e+02 4.406e+02, threshold=4.227e+02, percent-clipped=0.1
2024-08-06 17:25:12,914 INFO [trainer.py:765] (3/8) Epoch 14, batch 600, train_loss[loss=2.893, NarTop10Accuracy=0.7513, over 5769.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.6781, over 5668.24 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,548 INFO [trainer.py:765] (3/8) Epoch 14, batch 700, train_loss[loss=3.274, NarTop10Accuracy=0.6677, over 5202.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6817, over 5732.94 frames. ], batch size: 6, lr: 6.19e-03
2024-08-06 17:26:25,279 INFO [trainer.py:765] (3/8) Epoch 14, batch 800, train_loss[loss=3.034, NarTop10Accuracy=0.7229, over 5157.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6837, over 5784.65 frames. ], batch size: 6, lr: 6.18e-03
2024-08-06 17:26:57,659 INFO [trainer.py:765] (3/8) Epoch 14, batch 900, train_loss[loss=3.277, NarTop10Accuracy=0.6666, over 6147.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6848, over 5811.54 frames. ], batch size: 13, lr: 6.17e-03
2024-08-06 17:27:31,717 INFO [trainer.py:765] (3/8) Epoch 14, batch 1000, train_loss[loss=3.402, NarTop10Accuracy=0.6549, over 6348.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6811, over 5913.28 frames. ], batch size: 13, lr: 6.16e-03
2024-08-06 17:28:11,597 INFO [trainer.py:765] (3/8) Epoch 14, batch 1100, train_loss[loss=3.061, NarTop10Accuracy=0.7146, over 6801.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6794, over 5945.49 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,734 INFO [trainer.py:765] (3/8) Epoch 14, batch 1200, train_loss[loss=3.457, NarTop10Accuracy=0.6301, over 7212.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6807, over 5943.32 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,214 INFO [trainer.py:765] (3/8) Epoch 14, batch 1300, train_loss[loss=3.467, NarTop10Accuracy=0.6291, over 5070.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6804, over 6002.81 frames. ], batch size: 6, lr: 6.14e-03
2024-08-06 17:29:54,602 INFO [trainer.py:765] (3/8) Epoch 14, batch 1400, train_loss[loss=3.567, NarTop10Accuracy=0.6104, over 6117.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6785, over 6019.18 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,315 INFO [trainer.py:765] (3/8) Epoch 14, batch 1500, train_loss[loss=3.719, NarTop10Accuracy=0.58, over 7005.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6773, over 5948.23 frames. ], batch size: 50, lr: 6.12e-03
2024-08-06 17:30:53,044 INFO [trainer.py:765] (3/8) Epoch 14, batch 1600, train_loss[loss=2.946, NarTop10Accuracy=0.7398, over 7038.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.68, over 5929.67 frames. ], batch size: 22, lr: 6.11e-03
2024-08-06 17:31:19,729 INFO [trainer.py:765] (3/8) Epoch 14, batch 1700, train_loss[loss=3.247, NarTop10Accuracy=0.6836, over 6303.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6845, over 5911.94 frames. ], batch size: 13, lr: 6.10e-03
2024-08-06 17:31:46,290 INFO [trainer.py:765] (3/8) Epoch 14, batch 1800, train_loss[loss=2.979, NarTop10Accuracy=0.7251, over 6957.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6885, over 5971.40 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,727 INFO [trainer.py:765] (3/8) Epoch 14, batch 1900, train_loss[loss=3.68, NarTop10Accuracy=0.5826, over 6240.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6849, over 6015.21 frames. ], batch size: 50, lr: 6.09e-03
2024-08-06 17:32:38,282 INFO [trainer.py:765] (3/8) Epoch 14, batch 2000, train_loss[loss=3.308, NarTop10Accuracy=0.6772, over 5973.00 frames. ], tot_loss[loss=3.214, NarTop10Accuracy=0.6829, over 5976.40 frames. ], batch size: 50, lr: 6.08e-03
2024-08-06 17:33:03,646 INFO [trainer.py:765] (3/8) Epoch 14, batch 2100, train_loss[loss=2.992, NarTop10Accuracy=0.7204, over 4794.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6802, over 5963.96 frames. ], batch size: 5, lr: 6.07e-03
2024-08-06 17:33:28,999 INFO [trainer.py:765] (3/8) Epoch 14, batch 2200, train_loss[loss=3.219, NarTop10Accuracy=0.6862, over 7470.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6825, over 6006.62 frames. ], batch size: 32, lr: 6.06e-03
2024-08-06 17:33:54,087 INFO [trainer.py:765] (3/8) Epoch 14, batch 2300, train_loss[loss=2.857, NarTop10Accuracy=0.7672, over 5652.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6787, over 6004.24 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,534 INFO [trainer.py:765] (3/8) Epoch 14, batch 2400, train_loss[loss=2.794, NarTop10Accuracy=0.7644, over 5106.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6794, over 5789.51 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (3/8) Epoch 14, batch 2500, train_loss[loss=2.916, NarTop10Accuracy=0.7467, over 5076.00 frames. ], tot_loss[loss=3.199, NarTop10Accuracy=0.6858, over 5480.32 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,395 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (3/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:34:53,679 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.574e+02 1.975e+02 2.132e+02 2.304e+02 3.875e+02, threshold=4.265e+02, percent-clipped=0.0
2024-08-06 17:35:09,747 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 17:36:11,738 INFO [trainer.py:765] (3/8) Epoch 15, batch 100, train_loss[loss=3.068, NarTop10Accuracy=0.7138, over 7395.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6815, over 2361.87 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (3/8) Epoch 15, batch 200, train_loss[loss=3.496, NarTop10Accuracy=0.6313, over 6852.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 3864.00 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,714 INFO [trainer.py:765] (3/8) Epoch 15, batch 300, train_loss[loss=3.277, NarTop10Accuracy=0.6728, over 7104.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6877, over 4651.36 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,903 INFO [trainer.py:765] (3/8) Epoch 15, batch 400, train_loss[loss=2.894, NarTop10Accuracy=0.7573, over 5100.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6883, over 5098.52 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,353 INFO [trainer.py:765] (3/8) Epoch 15, batch 500, train_loss[loss=2.835, NarTop10Accuracy=0.7538, over 6102.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6879, over 5376.32 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,093 INFO [trainer.py:765] (3/8) Epoch 15, batch 600, train_loss[loss=2.919, NarTop10Accuracy=0.744, over 5577.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6859, over 5654.99 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,922 INFO [trainer.py:765] (3/8) Epoch 15, batch 700, train_loss[loss=2.933, NarTop10Accuracy=0.742, over 5109.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6844, over 5730.57 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,564 INFO [trainer.py:765] (3/8) Epoch 15, batch 800, train_loss[loss=3.263, NarTop10Accuracy=0.6725, over 5109.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6801, over 5767.87 frames. ], batch size: 6, lr: 5.76e-03
2024-08-06 17:40:35,790 INFO [trainer.py:765] (3/8) Epoch 15, batch 900, train_loss[loss=3.415, NarTop10Accuracy=0.6463, over 6285.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6839, over 5767.00 frames. ], batch size: 13, lr: 5.76e-03
2024-08-06 17:41:11,250 INFO [trainer.py:765] (3/8) Epoch 15, batch 1000, train_loss[loss=3.134, NarTop10Accuracy=0.6954, over 6237.00 frames. ], tot_loss[loss=3.199, NarTop10Accuracy=0.6863, over 5871.37 frames. ], batch size: 13, lr: 5.75e-03
2024-08-06 17:41:46,451 INFO [trainer.py:765] (3/8) Epoch 15, batch 1100, train_loss[loss=3.138, NarTop10Accuracy=0.6955, over 6861.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.686, over 5900.28 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,455 INFO [trainer.py:765] (3/8) Epoch 15, batch 1200, train_loss[loss=3.435, NarTop10Accuracy=0.6403, over 7254.00 frames. ], tot_loss[loss=3.227, NarTop10Accuracy=0.6803, over 5917.97 frames. ], batch size: 31, lr: 5.73e-03
2024-08-06 17:42:54,427 INFO [trainer.py:765] (3/8) Epoch 15, batch 1300, train_loss[loss=2.94, NarTop10Accuracy=0.731, over 5097.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.6847, over 5989.46 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,606 INFO [trainer.py:765] (3/8) Epoch 15, batch 1400, train_loss[loss=3.354, NarTop10Accuracy=0.6515, over 6162.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6824, over 6006.26 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,557 INFO [trainer.py:765] (3/8) Epoch 15, batch 1500, train_loss[loss=3.131, NarTop10Accuracy=0.7047, over 5826.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6821, over 5939.63 frames. ], batch size: 50, lr: 5.71e-03
2024-08-06 17:44:24,240 INFO [trainer.py:765] (3/8) Epoch 15, batch 1600, train_loss[loss=3.644, NarTop10Accuracy=0.6004, over 6930.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6856, over 5909.55 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,855 INFO [trainer.py:765] (3/8) Epoch 15, batch 1700, train_loss[loss=3.076, NarTop10Accuracy=0.7158, over 6579.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6866, over 5899.61 frames. ], batch size: 14, lr: 5.70e-03
2024-08-06 17:45:17,293 INFO [trainer.py:765] (3/8) Epoch 15, batch 1800, train_loss[loss=3.133, NarTop10Accuracy=0.6973, over 6984.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6871, over 5966.99 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,678 INFO [trainer.py:765] (3/8) Epoch 15, batch 1900, train_loss[loss=3.113, NarTop10Accuracy=0.7069, over 6330.00 frames. ], tot_loss[loss=3.214, NarTop10Accuracy=0.6833, over 6025.36 frames. ], batch size: 50, lr: 5.68e-03
2024-08-06 17:45:53,539 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:46:01,743 INFO [trainer.py:811] (3/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:46:02,217 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.631e+02 2.004e+02 2.149e+02 2.324e+02 3.721e+02, threshold=4.298e+02, percent-clipped=0.0
2024-08-06 17:46:17,372 INFO [trainer.py:765] (3/8) Epoch 15, batch 2000, train_loss[loss=3.211, NarTop10Accuracy=0.6827, over 6030.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6842, over 6010.76 frames. ], batch size: 50, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (3/8) Epoch 15, batch 2100, train_loss[loss=3.114, NarTop10Accuracy=0.7087, over 5001.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6855, over 5989.88 frames. ], batch size: 5, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (3/8) Epoch 15, batch 2200, train_loss[loss=3.082, NarTop10Accuracy=0.7139, over 7338.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6832, over 6012.88 frames. ], batch size: 31, lr: 5.66e-03
2024-08-06 17:47:33,291 INFO [trainer.py:765] (3/8) Epoch 15, batch 2300, train_loss[loss=3.472, NarTop10Accuracy=0.6308, over 5691.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.6831, over 6021.20 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,639 INFO [trainer.py:765] (3/8) Epoch 15, batch 2400, train_loss[loss=3.352, NarTop10Accuracy=0.6523, over 5067.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6877, over 5771.95 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,161 INFO [trainer.py:765] (3/8) Epoch 15, batch 2500, train_loss[loss=2.858, NarTop10Accuracy=0.7485, over 5106.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6934, over 5476.35 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:40,518 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 17:49:41,220 INFO [trainer.py:765] (3/8) Epoch 16, batch 100, train_loss[loss=3.494, NarTop10Accuracy=0.6262, over 7200.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6943, over 2347.86 frames. ], batch size: 31, lr: 5.45e-03
2024-08-06 17:50:12,156 INFO [trainer.py:765] (3/8) Epoch 16, batch 200, train_loss[loss=2.88, NarTop10Accuracy=0.7504, over 6864.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.687, over 3841.44 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,158 INFO [trainer.py:765] (3/8) Epoch 16, batch 300, train_loss[loss=3.166, NarTop10Accuracy=0.6962, over 6942.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6879, over 4645.42 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,975 INFO [trainer.py:765] (3/8) Epoch 16, batch 400, train_loss[loss=3.535, NarTop10Accuracy=0.6069, over 5085.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6875, over 5088.55 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,322 INFO [trainer.py:765] (3/8) Epoch 16, batch 500, train_loss[loss=2.945, NarTop10Accuracy=0.7435, over 6153.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6884, over 5364.16 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,250 INFO [trainer.py:765] (3/8) Epoch 16, batch 600, train_loss[loss=3.061, NarTop10Accuracy=0.7273, over 6192.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6868, over 5621.58 frames. ], batch size: 10, lr: 5.41e-03
2024-08-06 17:52:55,385 INFO [trainer.py:765] (3/8) Epoch 16, batch 700, train_loss[loss=3.019, NarTop10Accuracy=0.7217, over 4911.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6876, over 5690.42 frames. ], batch size: 6, lr: 5.41e-03
2024-08-06 17:53:33,814 INFO [trainer.py:765] (3/8) Epoch 16, batch 800, train_loss[loss=3.196, NarTop10Accuracy=0.6894, over 4914.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6899, over 5760.46 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,922 INFO [trainer.py:765] (3/8) Epoch 16, batch 900, train_loss[loss=3.468, NarTop10Accuracy=0.6265, over 6186.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6925, over 5808.52 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:54:37,606 INFO [trainer.py:765] (3/8) Epoch 16, batch 1000, train_loss[loss=2.995, NarTop10Accuracy=0.7268, over 6579.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6945, over 5917.13 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:55:17,195 INFO [trainer.py:765] (3/8) Epoch 16, batch 1100, train_loss[loss=3.238, NarTop10Accuracy=0.6813, over 6963.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6874, over 5932.87 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,208 INFO [trainer.py:765] (3/8) Epoch 16, batch 1200, train_loss[loss=3.526, NarTop10Accuracy=0.6218, over 7041.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6864, over 5914.22 frames. ], batch size: 31, lr: 5.37e-03
2024-08-06 17:56:22,774 INFO [trainer.py:765] (3/8) Epoch 16, batch 1300, train_loss[loss=3.328, NarTop10Accuracy=0.6628, over 5199.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6872, over 5980.74 frames. ], batch size: 6, lr: 5.37e-03
2024-08-06 17:56:44,647 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (3/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 17:56:54,007 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.620e+02 1.974e+02 2.136e+02 2.310e+02 5.351e+02, threshold=4.271e+02, percent-clipped=0.2
2024-08-06 17:57:06,171 INFO [trainer.py:765] (3/8) Epoch 16, batch 1400, train_loss[loss=3.157, NarTop10Accuracy=0.6927, over 6000.00 frames. ], tot_loss[loss=3.183, NarTop10Accuracy=0.6892, over 6009.62 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,033 INFO [trainer.py:765] (3/8) Epoch 16, batch 1500, train_loss[loss=3.409, NarTop10Accuracy=0.6477, over 5778.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6904, over 5962.80 frames. ], batch size: 50, lr: 5.35e-03
2024-08-06 17:58:01,774 INFO [trainer.py:765] (3/8) Epoch 16, batch 1600, train_loss[loss=2.937, NarTop10Accuracy=0.7389, over 7212.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6906, over 5927.19 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,475 INFO [trainer.py:765] (3/8) Epoch 16, batch 1700, train_loss[loss=2.915, NarTop10Accuracy=0.7477, over 6066.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6877, over 5925.09 frames. ], batch size: 13, lr: 5.34e-03
2024-08-06 17:58:54,975 INFO [trainer.py:765] (3/8) Epoch 16, batch 1800, train_loss[loss=3.071, NarTop10Accuracy=0.7099, over 7137.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6913, over 5967.98 frames. ], batch size: 22, lr: 5.33e-03
2024-08-06 17:59:21,359 INFO [trainer.py:765] (3/8) Epoch 16, batch 1900, train_loss[loss=3.341, NarTop10Accuracy=0.649, over 6531.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6851, over 6025.62 frames. ], batch size: 51, lr: 5.33e-03
2024-08-06 17:59:46,856 INFO [trainer.py:765] (3/8) Epoch 16, batch 2000, train_loss[loss=3.043, NarTop10Accuracy=0.7199, over 5652.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6909, over 5995.48 frames. ], batch size: 50, lr: 5.32e-03
2024-08-06 18:00:12,116 INFO [trainer.py:765] (3/8) Epoch 16, batch 2100, train_loss[loss=3.368, NarTop10Accuracy=0.6371, over 4746.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6851, over 5985.23 frames. ], batch size: 5, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (3/8) Epoch 16, batch 2200, train_loss[loss=3.142, NarTop10Accuracy=0.6997, over 7365.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6824, over 6021.73 frames. ], batch size: 31, lr: 5.31e-03
2024-08-06 18:01:02,502 INFO [trainer.py:765] (3/8) Epoch 16, batch 2300, train_loss[loss=3.138, NarTop10Accuracy=0.6978, over 5781.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6821, over 6024.07 frames. ], batch size: 9, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (3/8) Epoch 16, batch 2400, train_loss[loss=3.036, NarTop10Accuracy=0.7168, over 5166.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6861, over 5777.05 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,406 INFO [trainer.py:765] (3/8) Epoch 16, batch 2500, train_loss[loss=3.115, NarTop10Accuracy=0.7024, over 5184.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6926, over 5491.53 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,445 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (3/8) Epoch 17, batch 100, train_loss[loss=3.179, NarTop10Accuracy=0.6945, over 7326.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6997, over 2368.25 frames. ], batch size: 31, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (3/8) Epoch 17, batch 200, train_loss[loss=3.37, NarTop10Accuracy=0.6444, over 6912.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6961, over 3853.73 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,590 INFO [trainer.py:765] (3/8) Epoch 17, batch 300, train_loss[loss=3.309, NarTop10Accuracy=0.6638, over 7152.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6927, over 4659.82 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,401 INFO [trainer.py:765] (3/8) Epoch 17, batch 400, train_loss[loss=3.299, NarTop10Accuracy=0.6537, over 5094.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6926, over 5102.74 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,680 INFO [trainer.py:765] (3/8) Epoch 17, batch 500, train_loss[loss=2.878, NarTop10Accuracy=0.753, over 6177.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6958, over 5365.37 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (3/8) Epoch 17, batch 600, train_loss[loss=3.108, NarTop10Accuracy=0.7014, over 5763.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6923, over 5645.82 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (3/8) Epoch 17, batch 700, train_loss[loss=3.014, NarTop10Accuracy=0.7224, over 4905.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6936, over 5719.80 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:02,724 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (3/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,763 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 18:07:11,312 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.005e+02 2.161e+02 2.341e+02 3.806e+02, threshold=4.323e+02, percent-clipped=0.0
2024-08-06 18:07:14,353 INFO [trainer.py:765] (3/8) Epoch 17, batch 800, train_loss[loss=2.934, NarTop10Accuracy=0.7291, over 4983.00 frames. ], tot_loss[loss=3.18, NarTop10Accuracy=0.6897, over 5776.88 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (3/8) Epoch 17, batch 900, train_loss[loss=3.4, NarTop10Accuracy=0.6355, over 6642.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6953, over 5801.94 frames. ], batch size: 14, lr: 5.07e-03
2024-08-06 18:08:21,598 INFO [trainer.py:765] (3/8) Epoch 17, batch 1000, train_loss[loss=3.214, NarTop10Accuracy=0.6941, over 6543.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.693, over 5903.23 frames. ], batch size: 14, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (3/8) Epoch 17, batch 1100, train_loss[loss=2.938, NarTop10Accuracy=0.7429, over 6780.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6906, over 5939.96 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,746 INFO [trainer.py:765] (3/8) Epoch 17, batch 1200, train_loss[loss=3.159, NarTop10Accuracy=0.6989, over 6963.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6916, over 5936.70 frames. ], batch size: 31, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (3/8) Epoch 17, batch 1300, train_loss[loss=3.341, NarTop10Accuracy=0.6597, over 4959.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6911, over 6006.75 frames. ], batch size: 6, lr: 5.05e-03
2024-08-06 18:10:48,026 INFO [trainer.py:765] (3/8) Epoch 17, batch 1400, train_loss[loss=3.332, NarTop10Accuracy=0.6669, over 5919.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6896, over 6007.29 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,105 INFO [trainer.py:765] (3/8) Epoch 17, batch 1500, train_loss[loss=3.526, NarTop10Accuracy=0.6224, over 5577.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6928, over 5938.72 frames. ], batch size: 50, lr: 5.04e-03
2024-08-06 18:11:46,855 INFO [trainer.py:765] (3/8) Epoch 17, batch 1600, train_loss[loss=3.16, NarTop10Accuracy=0.6962, over 7107.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6958, over 5933.70 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,509 INFO [trainer.py:765] (3/8) Epoch 17, batch 1700, train_loss[loss=3.51, NarTop10Accuracy=0.6271, over 6282.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 5911.31 frames. ], batch size: 13, lr: 5.03e-03
2024-08-06 18:12:40,002 INFO [trainer.py:765] (3/8) Epoch 17, batch 1800, train_loss[loss=2.848, NarTop10Accuracy=0.7576, over 7050.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6879, over 5972.83 frames. ], batch size: 22, lr: 5.02e-03
2024-08-06 18:13:06,380 INFO [trainer.py:765] (3/8) Epoch 17, batch 1900, train_loss[loss=3.09, NarTop10Accuracy=0.7039, over 6243.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6864, over 6030.06 frames. ], batch size: 50, lr: 5.01e-03
2024-08-06 18:13:31,923 INFO [trainer.py:765] (3/8) Epoch 17, batch 2000, train_loss[loss=3.567, NarTop10Accuracy=0.6098, over 6174.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6907, over 5999.84 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (3/8) Epoch 17, batch 2100, train_loss[loss=2.896, NarTop10Accuracy=0.7481, over 4797.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6897, over 5968.81 frames. ], batch size: 5, lr: 5.00e-03
2024-08-06 18:14:22,434 INFO [trainer.py:765] (3/8) Epoch 17, batch 2200, train_loss[loss=3.108, NarTop10Accuracy=0.7146, over 7035.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6857, over 6022.33 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (3/8) Epoch 17, batch 2300, train_loss[loss=2.985, NarTop10Accuracy=0.73, over 5862.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.687, over 6027.85 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (3/8) Epoch 17, batch 2400, train_loss[loss=2.959, NarTop10Accuracy=0.7368, over 5082.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 5780.90 frames. ], batch size: 7, lr: 4.99e-03
2024-08-06 18:15:35,515 INFO [trainer.py:765] (3/8) Epoch 17, batch 2500, train_loss[loss=2.779, NarTop10Accuracy=0.7657, over 5124.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6913, over 5475.42 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:56,000 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 18:16:49,908 INFO [trainer.py:765] (3/8) Epoch 18, batch 100, train_loss[loss=3.111, NarTop10Accuracy=0.7048, over 7329.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.688, over 2367.70 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (3/8) Epoch 18, batch 200, train_loss[loss=2.828, NarTop10Accuracy=0.7648, over 6891.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6946, over 3864.70 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,716 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 18:17:35,927 INFO [trainer.py:811] (3/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 18:17:36,529 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.024e+02 2.164e+02 2.334e+02 7.024e+02, threshold=4.329e+02, percent-clipped=0.1
2024-08-06 18:18:06,912 INFO [trainer.py:765] (3/8) Epoch 18, batch 300, train_loss[loss=3.349, NarTop10Accuracy=0.6575, over 7206.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6942, over 4680.02 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (3/8) Epoch 18, batch 400, train_loss[loss=3.446, NarTop10Accuracy=0.6373, over 5151.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6958, over 5126.11 frames. ], batch size: 7, lr: 4.81e-03
2024-08-06 18:19:13,599 INFO [trainer.py:765] (3/8) Epoch 18, batch 500, train_loss[loss=3.129, NarTop10Accuracy=0.6975, over 6036.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6952, over 5401.99 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (3/8) Epoch 18, batch 600, train_loss[loss=3.572, NarTop10Accuracy=0.6106, over 5823.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6949, over 5673.84 frames. ], batch size: 9, lr: 4.80e-03
2024-08-06 18:20:23,870 INFO [trainer.py:765] (3/8) Epoch 18, batch 700, train_loss[loss=3.645, NarTop10Accuracy=0.5994, over 5103.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6924, over 5749.70 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,026 INFO [trainer.py:765] (3/8) Epoch 18, batch 800, train_loss[loss=2.932, NarTop10Accuracy=0.7486, over 4977.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6913, over 5801.66 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,409 INFO [trainer.py:765] (3/8) Epoch 18, batch 900, train_loss[loss=2.999, NarTop10Accuracy=0.7255, over 6243.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6967, over 5814.56 frames. ], batch size: 13, lr: 4.79e-03
2024-08-06 18:22:11,192 INFO [trainer.py:765] (3/8) Epoch 18, batch 1000, train_loss[loss=2.866, NarTop10Accuracy=0.7543, over 6657.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6931, over 5900.22 frames. ], batch size: 14, lr: 4.78e-03
2024-08-06 18:22:46,969 INFO [trainer.py:765] (3/8) Epoch 18, batch 1100, train_loss[loss=3.466, NarTop10Accuracy=0.6335, over 6861.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6943, over 5943.13 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (3/8) Epoch 18, batch 1200, train_loss[loss=3.59, NarTop10Accuracy=0.6085, over 7188.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.69, over 5921.31 frames. ], batch size: 31, lr: 4.77e-03
2024-08-06 18:24:00,100 INFO [trainer.py:765] (3/8) Epoch 18, batch 1300, train_loss[loss=2.929, NarTop10Accuracy=0.743, over 4215.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6944, over 5967.52 frames. ], batch size: 5, lr: 4.77e-03
2024-08-06 18:24:29,575 INFO [trainer.py:765] (3/8) Epoch 18, batch 1400, train_loss[loss=3.013, NarTop10Accuracy=0.7198, over 5970.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.694, over 5992.22 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (3/8) Epoch 18, batch 1500, train_loss[loss=3.127, NarTop10Accuracy=0.7085, over 6060.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6943, over 5924.67 frames. ], batch size: 52, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (3/8) Epoch 18, batch 1600, train_loss[loss=3.024, NarTop10Accuracy=0.7213, over 7335.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.692, over 5914.45 frames. ], batch size: 23, lr: 4.75e-03
2024-08-06 18:25:54,688 INFO [trainer.py:765] (3/8) Epoch 18, batch 1700, train_loss[loss=3.177, NarTop10Accuracy=0.6929, over 6717.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6919, over 5904.42 frames. ], batch size: 14, lr: 4.75e-03
2024-08-06 18:26:21,197 INFO [trainer.py:765] (3/8) Epoch 18, batch 1800, train_loss[loss=3.455, NarTop10Accuracy=0.6401, over 7086.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6933, over 5968.18 frames. ], batch size: 22, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (3/8) Epoch 18, batch 1900, train_loss[loss=3.065, NarTop10Accuracy=0.7199, over 6102.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6913, over 6017.15 frames. ], batch size: 50, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (3/8) Epoch 18, batch 2000, train_loss[loss=3.076, NarTop10Accuracy=0.7149, over 5895.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.694, over 5982.20 frames. ], batch size: 52, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (3/8) Epoch 18, batch 2100, train_loss[loss=3.337, NarTop10Accuracy=0.6571, over 4773.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6951, over 5965.50 frames. ], batch size: 5, lr: 4.73e-03
2024-08-06 18:28:03,813 INFO [trainer.py:765] (3/8) Epoch 18, batch 2200, train_loss[loss=3.087, NarTop10Accuracy=0.7164, over 7419.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6952, over 6006.21 frames. ], batch size: 32, lr: 4.72e-03
2024-08-06 18:28:06,572 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 18:28:14,650 INFO [trainer.py:811] (3/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.654e+02 2.054e+02 2.220e+02 2.384e+02 3.992e+02, threshold=4.441e+02, percent-clipped=0.0
2024-08-06 18:28:37,097 INFO [trainer.py:765] (3/8) Epoch 18, batch 2300, train_loss[loss=2.882, NarTop10Accuracy=0.7441, over 5577.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6918, over 6025.36 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,592 INFO [trainer.py:765] (3/8) Epoch 18, batch 2400, train_loss[loss=2.741, NarTop10Accuracy=0.7797, over 5202.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6965, over 5754.26 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (3/8) Epoch 18, batch 2500, train_loss[loss=3.075, NarTop10Accuracy=0.7098, over 5271.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7005, over 5467.59 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,157 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 18:30:41,232 INFO [trainer.py:765] (3/8) Epoch 19, batch 100, train_loss[loss=3.003, NarTop10Accuracy=0.723, over 7362.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6941, over 2358.44 frames. ], batch size: 31, lr: 4.57e-03
2024-08-06 18:31:15,603 INFO [trainer.py:765] (3/8) Epoch 19, batch 200, train_loss[loss=3.106, NarTop10Accuracy=0.7087, over 6837.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6952, over 3850.90 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (3/8) Epoch 19, batch 300, train_loss[loss=3.453, NarTop10Accuracy=0.6288, over 6978.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6986, over 4662.01 frames. ], batch size: 22, lr: 4.56e-03
2024-08-06 18:32:20,356 INFO [trainer.py:765] (3/8) Epoch 19, batch 400, train_loss[loss=3.202, NarTop10Accuracy=0.6821, over 5145.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6983, over 5114.69 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (3/8) Epoch 19, batch 500, train_loss[loss=2.949, NarTop10Accuracy=0.7405, over 5997.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6987, over 5384.27 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (3/8) Epoch 19, batch 600, train_loss[loss=3.194, NarTop10Accuracy=0.6847, over 5688.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6976, over 5665.53 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (3/8) Epoch 19, batch 700, train_loss[loss=2.875, NarTop10Accuracy=0.7469, over 5100.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6966, over 5726.51 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (3/8) Epoch 19, batch 800, train_loss[loss=3.044, NarTop10Accuracy=0.7243, over 4263.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6951, over 5786.05 frames. ], batch size: 5, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (3/8) Epoch 19, batch 900, train_loss[loss=2.808, NarTop10Accuracy=0.7611, over 6237.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.697, over 5791.85 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:35:48,637 INFO [trainer.py:765] (3/8) Epoch 19, batch 1000, train_loss[loss=3.423, NarTop10Accuracy=0.6343, over 6222.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6961, over 5902.56 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:36:20,939 INFO [trainer.py:765] (3/8) Epoch 19, batch 1100, train_loss[loss=2.998, NarTop10Accuracy=0.7241, over 6840.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6939, over 5922.96 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (3/8) Epoch 19, batch 1200, train_loss[loss=2.94, NarTop10Accuracy=0.7447, over 7551.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6919, over 5925.72 frames. ], batch size: 32, lr: 4.52e-03
2024-08-06 18:37:35,315 INFO [trainer.py:765] (3/8) Epoch 19, batch 1300, train_loss[loss=3.009, NarTop10Accuracy=0.7266, over 4989.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6936, over 6001.20 frames. ], batch size: 6, lr: 4.51e-03
2024-08-06 18:38:04,680 INFO [trainer.py:765] (3/8) Epoch 19, batch 1400, train_loss[loss=2.923, NarTop10Accuracy=0.7446, over 6192.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6943, over 6026.05 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,551 INFO [trainer.py:765] (3/8) Epoch 19, batch 1500, train_loss[loss=3.458, NarTop10Accuracy=0.6319, over 6372.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6974, over 5953.83 frames. ], batch size: 51, lr: 4.50e-03
2024-08-06 18:39:02,312 INFO [trainer.py:765] (3/8) Epoch 19, batch 1600, train_loss[loss=3.542, NarTop10Accuracy=0.6186, over 7170.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6968, over 5928.91 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,590 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (3/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,796 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 18:39:20,378 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.633e+02 2.040e+02 2.194e+02 2.364e+02 6.410e+02, threshold=4.387e+02, percent-clipped=0.2
2024-08-06 18:39:37,191 INFO [trainer.py:765] (3/8) Epoch 19, batch 1700, train_loss[loss=3.411, NarTop10Accuracy=0.6326, over 6249.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6956, over 5933.69 frames. ], batch size: 13, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (3/8) Epoch 19, batch 1800, train_loss[loss=3.517, NarTop10Accuracy=0.6163, over 6888.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6953, over 5991.15 frames. ], batch size: 22, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (3/8) Epoch 19, batch 1900, train_loss[loss=3.127, NarTop10Accuracy=0.7052, over 6135.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6968, over 6029.66 frames. ], batch size: 50, lr: 4.49e-03
2024-08-06 18:40:55,793 INFO [trainer.py:765] (3/8) Epoch 19, batch 2000, train_loss[loss=3.342, NarTop10Accuracy=0.6635, over 5445.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6955, over 6010.44 frames. ], batch size: 50, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (3/8) Epoch 19, batch 2100, train_loss[loss=2.801, NarTop10Accuracy=0.7669, over 4926.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6993, over 5985.33 frames. ], batch size: 5, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (3/8) Epoch 19, batch 2200, train_loss[loss=3.076, NarTop10Accuracy=0.7065, over 7092.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6968, over 6030.98 frames. ], batch size: 31, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (3/8) Epoch 19, batch 2300, train_loss[loss=3.164, NarTop10Accuracy=0.6917, over 5745.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6926, over 6035.13 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,987 INFO [trainer.py:765] (3/8) Epoch 19, batch 2400, train_loss[loss=3.002, NarTop10Accuracy=0.7272, over 5109.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6963, over 5771.22 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:42:59,690 INFO [trainer.py:765] (3/8) Epoch 19, batch 2500, train_loss[loss=2.813, NarTop10Accuracy=0.7672, over 5088.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7002, over 5467.67 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,696 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 18:44:22,973 INFO [trainer.py:765] (3/8) Epoch 20, batch 100, train_loss[loss=3.254, NarTop10Accuracy=0.6777, over 7131.00 frames. ], tot_loss[loss=3.179, NarTop10Accuracy=0.69, over 2366.38 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (3/8) Epoch 20, batch 200, train_loss[loss=3.53, NarTop10Accuracy=0.6176, over 6765.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6992, over 3873.91 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,278 INFO [trainer.py:765] (3/8) Epoch 20, batch 300, train_loss[loss=3.367, NarTop10Accuracy=0.6455, over 7083.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7023, over 4684.55 frames. ], batch size: 22, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (3/8) Epoch 20, batch 400, train_loss[loss=2.818, NarTop10Accuracy=0.7595, over 5184.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7018, over 5131.92 frames. ], batch size: 7, lr: 4.32e-03
2024-08-06 18:46:35,769 INFO [trainer.py:765] (3/8) Epoch 20, batch 500, train_loss[loss=2.788, NarTop10Accuracy=0.7673, over 6051.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6995, over 5394.39 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,254 INFO [trainer.py:765] (3/8) Epoch 20, batch 600, train_loss[loss=3.12, NarTop10Accuracy=0.6958, over 5733.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7002, over 5659.22 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (3/8) Epoch 20, batch 700, train_loss[loss=2.759, NarTop10Accuracy=0.778, over 4242.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7015, over 5712.59 frames. ], batch size: 5, lr: 4.31e-03
2024-08-06 18:48:21,015 INFO [trainer.py:765] (3/8) Epoch 20, batch 800, train_loss[loss=2.798, NarTop10Accuracy=0.7666, over 5121.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6989, over 5769.36 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:56,534 INFO [trainer.py:765] (3/8) Epoch 20, batch 900, train_loss[loss=2.951, NarTop10Accuracy=0.7414, over 6129.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7004, over 5782.37 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (3/8) Epoch 20, batch 1000, train_loss[loss=3.275, NarTop10Accuracy=0.6742, over 6597.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6961, over 5882.83 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:52,236 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 18:50:00,327 INFO [trainer.py:811] (3/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,327 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 18:50:00,875 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.681e+02 2.061e+02 2.223e+02 2.401e+02 3.871e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 18:50:15,427 INFO [trainer.py:765] (3/8) Epoch 20, batch 1100, train_loss[loss=3.284, NarTop10Accuracy=0.6681, over 6747.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6976, over 5928.00 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,776 INFO [trainer.py:765] (3/8) Epoch 20, batch 1200, train_loss[loss=2.933, NarTop10Accuracy=0.7388, over 7200.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6969, over 5913.91 frames. ], batch size: 32, lr: 4.29e-03
2024-08-06 18:51:25,130 INFO [trainer.py:765] (3/8) Epoch 20, batch 1300, train_loss[loss=3.314, NarTop10Accuracy=0.6573, over 5106.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6986, over 5966.18 frames. ], batch size: 6, lr: 4.29e-03
2024-08-06 18:51:59,315 INFO [trainer.py:765] (3/8) Epoch 20, batch 1400, train_loss[loss=3.102, NarTop10Accuracy=0.6999, over 6117.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6994, over 5995.93 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,806 INFO [trainer.py:765] (3/8) Epoch 20, batch 1500, train_loss[loss=3.286, NarTop10Accuracy=0.6701, over 6207.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6969, over 5930.60 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (3/8) Epoch 20, batch 1600, train_loss[loss=2.984, NarTop10Accuracy=0.7328, over 7026.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6956, over 5911.21 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,328 INFO [trainer.py:765] (3/8) Epoch 20, batch 1700, train_loss[loss=3.549, NarTop10Accuracy=0.6146, over 6303.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6966, over 5894.56 frames. ], batch size: 13, lr: 4.27e-03
2024-08-06 18:53:53,851 INFO [trainer.py:765] (3/8) Epoch 20, batch 1800, train_loss[loss=3.059, NarTop10Accuracy=0.719, over 7062.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6978, over 5965.81 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,316 INFO [trainer.py:765] (3/8) Epoch 20, batch 1900, train_loss[loss=3.094, NarTop10Accuracy=0.7085, over 5967.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6944, over 6002.43 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:54:45,890 INFO [trainer.py:765] (3/8) Epoch 20, batch 2000, train_loss[loss=3.634, NarTop10Accuracy=0.597, over 5934.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6941, over 5982.52 frames. ], batch size: 51, lr: 4.26e-03
2024-08-06 18:55:11,183 INFO [trainer.py:765] (3/8) Epoch 20, batch 2100, train_loss[loss=3.062, NarTop10Accuracy=0.699, over 3966.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6958, over 5967.51 frames. ], batch size: 4, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (3/8) Epoch 20, batch 2200, train_loss[loss=2.928, NarTop10Accuracy=0.7398, over 7338.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.695, over 6003.09 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,636 INFO [trainer.py:765] (3/8) Epoch 20, batch 2300, train_loss[loss=3.165, NarTop10Accuracy=0.695, over 5778.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.693, over 6009.76 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,050 INFO [trainer.py:765] (3/8) Epoch 20, batch 2400, train_loss[loss=3.002, NarTop10Accuracy=0.7276, over 5103.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6947, over 5762.67 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,566 INFO [trainer.py:765] (3/8) Epoch 20, batch 2500, train_loss[loss=2.802, NarTop10Accuracy=0.7647, over 5307.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7031, over 5466.68 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:57:09,699 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (3/8) Epoch 21, batch 100, train_loss[loss=3.331, NarTop10Accuracy=0.6594, over 7170.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7035, over 2365.79 frames. ], batch size: 31, lr: 4.13e-03
2024-08-06 18:58:40,417 INFO [trainer.py:765] (3/8) Epoch 21, batch 200, train_loss[loss=2.869, NarTop10Accuracy=0.7526, over 6696.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7017, over 3865.50 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,333 INFO [trainer.py:765] (3/8) Epoch 21, batch 300, train_loss[loss=2.901, NarTop10Accuracy=0.7411, over 7032.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6998, over 4672.59 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,150 INFO [trainer.py:765] (3/8) Epoch 21, batch 400, train_loss[loss=2.874, NarTop10Accuracy=0.7578, over 5043.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7032, over 5116.84 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,839 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:00:25,075 INFO [trainer.py:811] (3/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,076 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:00:25,622 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,891 INFO [trainer.py:765] (3/8) Epoch 21, batch 500, train_loss[loss=2.741, NarTop10Accuracy=0.7795, over 6057.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7022, over 5375.13 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,329 INFO [trainer.py:765] (3/8) Epoch 21, batch 600, train_loss[loss=3.283, NarTop10Accuracy=0.6601, over 6192.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7055, over 5630.47 frames. ], batch size: 10, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (3/8) Epoch 21, batch 700, train_loss[loss=2.876, NarTop10Accuracy=0.7556, over 5184.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7017, over 5698.72 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (3/8) Epoch 21, batch 800, train_loss[loss=3.163, NarTop10Accuracy=0.703, over 4956.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6995, over 5780.96 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (3/8) Epoch 21, batch 900, train_loss[loss=2.887, NarTop10Accuracy=0.7457, over 6654.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6992, over 5804.05 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:03:25,801 INFO [trainer.py:765] (3/8) Epoch 21, batch 1000, train_loss[loss=2.833, NarTop10Accuracy=0.7589, over 6216.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6989, over 5903.68 frames. ], batch size: 13, lr: 4.09e-03
2024-08-06 19:04:07,207 INFO [trainer.py:765] (3/8) Epoch 21, batch 1100, train_loss[loss=3.486, NarTop10Accuracy=0.6312, over 6588.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6951, over 5925.46 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,463 INFO [trainer.py:765] (3/8) Epoch 21, batch 1200, train_loss[loss=3.28, NarTop10Accuracy=0.6679, over 7365.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6996, over 5930.70 frames. ], batch size: 32, lr: 4.08e-03
2024-08-06 19:05:15,316 INFO [trainer.py:765] (3/8) Epoch 21, batch 1300, train_loss[loss=2.86, NarTop10Accuracy=0.7518, over 4362.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7036, over 5995.69 frames. ], batch size: 5, lr: 4.08e-03
2024-08-06 19:05:55,559 INFO [trainer.py:765] (3/8) Epoch 21, batch 1400, train_loss[loss=3.478, NarTop10Accuracy=0.6203, over 6033.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.703, over 6014.45 frames. ], batch size: 11, lr: 4.07e-03
2024-08-06 19:06:23,600 INFO [trainer.py:765] (3/8) Epoch 21, batch 1500, train_loss[loss=3.293, NarTop10Accuracy=0.6645, over 6168.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7007, over 5946.14 frames. ], batch size: 50, lr: 4.07e-03
2024-08-06 19:06:51,462 INFO [trainer.py:765] (3/8) Epoch 21, batch 1600, train_loss[loss=2.8, NarTop10Accuracy=0.7706, over 7029.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6999, over 5925.26 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,212 INFO [trainer.py:765] (3/8) Epoch 21, batch 1700, train_loss[loss=3.169, NarTop10Accuracy=0.6954, over 6615.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.699, over 5933.65 frames. ], batch size: 14, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (3/8) Epoch 21, batch 1800, train_loss[loss=3.031, NarTop10Accuracy=0.723, over 6816.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6995, over 5980.32 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,369 INFO [trainer.py:765] (3/8) Epoch 21, batch 1900, train_loss[loss=3.638, NarTop10Accuracy=0.5947, over 6075.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6974, over 6019.32 frames. ], batch size: 53, lr: 4.06e-03
2024-08-06 19:08:37,105 INFO [trainer.py:765] (3/8) Epoch 21, batch 2000, train_loss[loss=3.47, NarTop10Accuracy=0.6309, over 6591.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6979, over 6000.97 frames. ], batch size: 50, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (3/8) Epoch 21, batch 2100, train_loss[loss=2.903, NarTop10Accuracy=0.7399, over 3945.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6963, over 5996.07 frames. ], batch size: 4, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (3/8) Epoch 21, batch 2200, train_loss[loss=2.918, NarTop10Accuracy=0.7435, over 7437.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6955, over 6030.04 frames. ], batch size: 32, lr: 4.04e-03
2024-08-06 19:09:53,223 INFO [trainer.py:765] (3/8) Epoch 21, batch 2300, train_loss[loss=3.157, NarTop10Accuracy=0.7057, over 5742.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6928, over 6029.69 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,597 INFO [trainer.py:765] (3/8) Epoch 21, batch 2400, train_loss[loss=3.345, NarTop10Accuracy=0.6408, over 5022.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6963, over 5764.97 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,230 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (3/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,275 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.703e+02 2.100e+02 2.242e+02 2.407e+02 6.546e+02, threshold=4.484e+02, percent-clipped=0.1
2024-08-06 19:10:49,272 INFO [trainer.py:765] (3/8) Epoch 21, batch 2500, train_loss[loss=3.375, NarTop10Accuracy=0.649, over 5022.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7042, over 5474.58 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:09,185 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 19:12:09,054 INFO [trainer.py:765] (3/8) Epoch 22, batch 100, train_loss[loss=2.838, NarTop10Accuracy=0.7642, over 7071.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7074, over 2360.08 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (3/8) Epoch 22, batch 200, train_loss[loss=3.196, NarTop10Accuracy=0.6922, over 6717.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7064, over 3851.68 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (3/8) Epoch 22, batch 300, train_loss[loss=2.913, NarTop10Accuracy=0.7563, over 7014.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7066, over 4663.73 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,229 INFO [trainer.py:765] (3/8) Epoch 22, batch 400, train_loss[loss=2.818, NarTop10Accuracy=0.7628, over 5061.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7082, over 5106.34 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (3/8) Epoch 22, batch 500, train_loss[loss=3.128, NarTop10Accuracy=0.7051, over 6039.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7074, over 5384.79 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (3/8) Epoch 22, batch 600, train_loss[loss=2.994, NarTop10Accuracy=0.7368, over 5799.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7018, over 5646.22 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (3/8) Epoch 22, batch 700, train_loss[loss=3.426, NarTop10Accuracy=0.6347, over 5010.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7016, over 5719.62 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:10,665 INFO [trainer.py:765] (3/8) Epoch 22, batch 800, train_loss[loss=2.888, NarTop10Accuracy=0.7428, over 4326.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7027, over 5773.07 frames. ], batch size: 5, lr: 3.91e-03
2024-08-06 19:16:40,952 INFO [trainer.py:765] (3/8) Epoch 22, batch 900, train_loss[loss=3.011, NarTop10Accuracy=0.725, over 6207.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7025, over 5797.93 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:16,433 INFO [trainer.py:765] (3/8) Epoch 22, batch 1000, train_loss[loss=3.076, NarTop10Accuracy=0.7009, over 6285.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7039, over 5899.26 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:52,085 INFO [trainer.py:765] (3/8) Epoch 22, batch 1100, train_loss[loss=3.031, NarTop10Accuracy=0.7214, over 6798.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7022, over 5936.15 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,927 INFO [trainer.py:765] (3/8) Epoch 22, batch 1200, train_loss[loss=2.906, NarTop10Accuracy=0.7501, over 7353.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7057, over 5944.96 frames. ], batch size: 31, lr: 3.89e-03
2024-08-06 19:19:01,253 INFO [trainer.py:765] (3/8) Epoch 22, batch 1300, train_loss[loss=3.003, NarTop10Accuracy=0.7231, over 5073.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7068, over 6009.90 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,317 INFO [trainer.py:765] (3/8) Epoch 22, batch 1400, train_loss[loss=2.885, NarTop10Accuracy=0.7537, over 6231.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7038, over 6017.84 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (3/8) Epoch 22, batch 1500, train_loss[loss=3.462, NarTop10Accuracy=0.6328, over 5904.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7034, over 5940.48 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,646 INFO [trainer.py:765] (3/8) Epoch 22, batch 1600, train_loss[loss=3.054, NarTop10Accuracy=0.7173, over 7077.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7001, over 5909.04 frames. ], batch size: 22, lr: 3.88e-03
2024-08-06 19:20:58,418 INFO [trainer.py:765] (3/8) Epoch 22, batch 1700, train_loss[loss=3.2, NarTop10Accuracy=0.679, over 6534.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.6999, over 5912.10 frames. ], batch size: 14, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (3/8) Epoch 22, batch 1800, train_loss[loss=2.937, NarTop10Accuracy=0.7438, over 7149.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7012, over 5993.60 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (3/8) Epoch 22, batch 1900, train_loss[loss=3.1, NarTop10Accuracy=0.714, over 6096.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6972, over 6037.53 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:21:53,109 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (3/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.670e+02 2.114e+02 2.276e+02 2.445e+02 4.438e+02, threshold=4.551e+02, percent-clipped=0.0
2024-08-06 19:22:24,818 INFO [trainer.py:765] (3/8) Epoch 22, batch 2000, train_loss[loss=3.524, NarTop10Accuracy=0.6201, over 6570.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7009, over 6018.31 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (3/8) Epoch 22, batch 2100, train_loss[loss=3.121, NarTop10Accuracy=0.7042, over 4749.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7029, over 5998.21 frames. ], batch size: 5, lr: 3.86e-03
2024-08-06 19:23:15,229 INFO [trainer.py:765] (3/8) Epoch 22, batch 2200, train_loss[loss=2.984, NarTop10Accuracy=0.7309, over 7212.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 6038.52 frames. ], batch size: 31, lr: 3.86e-03
2024-08-06 19:23:40,314 INFO [trainer.py:765] (3/8) Epoch 22, batch 2300, train_loss[loss=3.086, NarTop10Accuracy=0.7081, over 6207.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6992, over 6044.30 frames. ], batch size: 10, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (3/8) Epoch 22, batch 2400, train_loss[loss=3.192, NarTop10Accuracy=0.6818, over 5772.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7012, over 5794.45 frames. ], batch size: 8, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (3/8) Epoch 22, batch 2500, train_loss[loss=3.199, NarTop10Accuracy=0.6757, over 5238.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7041, over 5488.57 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,439 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 19:25:45,385 INFO [trainer.py:765] (3/8) Epoch 23, batch 100, train_loss[loss=2.989, NarTop10Accuracy=0.7254, over 7125.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7014, over 2355.94 frames. ], batch size: 31, lr: 3.76e-03
2024-08-06 19:26:21,309 INFO [trainer.py:765] (3/8) Epoch 23, batch 200, train_loss[loss=3.444, NarTop10Accuracy=0.6411, over 6750.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7008, over 3848.34 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,603 INFO [trainer.py:765] (3/8) Epoch 23, batch 300, train_loss[loss=2.98, NarTop10Accuracy=0.7286, over 7059.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7052, over 4640.14 frames. ], batch size: 22, lr: 3.75e-03
2024-08-06 19:27:26,541 INFO [trainer.py:765] (3/8) Epoch 23, batch 400, train_loss[loss=3.356, NarTop10Accuracy=0.6481, over 5109.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7039, over 5100.64 frames. ], batch size: 7, lr: 3.75e-03
2024-08-06 19:27:59,713 INFO [trainer.py:765] (3/8) Epoch 23, batch 500, train_loss[loss=3.429, NarTop10Accuracy=0.6293, over 6003.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7024, over 5370.55 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,883 INFO [trainer.py:765] (3/8) Epoch 23, batch 600, train_loss[loss=3.351, NarTop10Accuracy=0.6568, over 5667.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7038, over 5639.80 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,367 INFO [trainer.py:765] (3/8) Epoch 23, batch 700, train_loss[loss=3.173, NarTop10Accuracy=0.6819, over 5226.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7063, over 5704.91 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:29:43,613 INFO [trainer.py:765] (3/8) Epoch 23, batch 800, train_loss[loss=2.859, NarTop10Accuracy=0.7549, over 4356.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.7043, over 5772.33 frames. ], batch size: 5, lr: 3.74e-03
2024-08-06 19:30:19,390 INFO [trainer.py:765] (3/8) Epoch 23, batch 900, train_loss[loss=3.221, NarTop10Accuracy=0.6821, over 6465.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7055, over 5793.73 frames. ], batch size: 14, lr: 3.73e-03
2024-08-06 19:30:58,195 INFO [trainer.py:765] (3/8) Epoch 23, batch 1000, train_loss[loss=2.951, NarTop10Accuracy=0.7337, over 6255.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7075, over 5916.19 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:31:31,521 INFO [trainer.py:765] (3/8) Epoch 23, batch 1100, train_loss[loss=3.043, NarTop10Accuracy=0.7202, over 6900.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7068, over 5938.15 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,518 INFO [trainer.py:765] (3/8) Epoch 23, batch 1200, train_loss[loss=3.071, NarTop10Accuracy=0.7192, over 7227.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7038, over 5933.80 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,937 INFO [trainer.py:765] (3/8) Epoch 23, batch 1300, train_loss[loss=3.077, NarTop10Accuracy=0.7085, over 5031.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.703, over 5982.56 frames. ], batch size: 6, lr: 3.72e-03
2024-08-06 19:32:56,402 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (3/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:33:05,263 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.759e+02 2.108e+02 2.273e+02 2.457e+02 3.966e+02, threshold=4.546e+02, percent-clipped=0.0
2024-08-06 19:33:27,407 INFO [trainer.py:765] (3/8) Epoch 23, batch 1400, train_loss[loss=2.77, NarTop10Accuracy=0.7739, over 6126.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.703, over 6005.93 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,216 INFO [trainer.py:765] (3/8) Epoch 23, batch 1500, train_loss[loss=3.296, NarTop10Accuracy=0.6705, over 5616.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.705, over 5954.33 frames. ], batch size: 50, lr: 3.71e-03
2024-08-06 19:34:26,015 INFO [trainer.py:765] (3/8) Epoch 23, batch 1600, train_loss[loss=2.902, NarTop10Accuracy=0.7511, over 7209.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7041, over 5939.75 frames. ], batch size: 22, lr: 3.71e-03
2024-08-06 19:34:52,783 INFO [trainer.py:765] (3/8) Epoch 23, batch 1700, train_loss[loss=3.31, NarTop10Accuracy=0.6642, over 6231.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7009, over 5912.73 frames. ], batch size: 13, lr: 3.71e-03
2024-08-06 19:35:19,262 INFO [trainer.py:765] (3/8) Epoch 23, batch 1800, train_loss[loss=2.95, NarTop10Accuracy=0.7429, over 7044.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7027, over 5975.65 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,597 INFO [trainer.py:765] (3/8) Epoch 23, batch 1900, train_loss[loss=3.43, NarTop10Accuracy=0.6371, over 6192.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.6999, over 6019.30 frames. ], batch size: 51, lr: 3.70e-03
2024-08-06 19:36:11,171 INFO [trainer.py:765] (3/8) Epoch 23, batch 2000, train_loss[loss=3.643, NarTop10Accuracy=0.5959, over 5631.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7023, over 5983.98 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:36,518 INFO [trainer.py:765] (3/8) Epoch 23, batch 2100, train_loss[loss=3.394, NarTop10Accuracy=0.6479, over 3936.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7032, over 5979.84 frames. ], batch size: 4, lr: 3.69e-03
2024-08-06 19:37:01,909 INFO [trainer.py:765] (3/8) Epoch 23, batch 2200, train_loss[loss=3.163, NarTop10Accuracy=0.6989, over 7005.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7004, over 6019.64 frames. ], batch size: 31, lr: 3.69e-03
2024-08-06 19:37:27,062 INFO [trainer.py:765] (3/8) Epoch 23, batch 2300, train_loss[loss=2.963, NarTop10Accuracy=0.7385, over 5592.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7026, over 6026.63 frames. ], batch size: 9, lr: 3.69e-03
2024-08-06 19:37:51,424 INFO [trainer.py:765] (3/8) Epoch 23, batch 2400, train_loss[loss=3.134, NarTop10Accuracy=0.6976, over 5226.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7029, over 5775.06 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,053 INFO [trainer.py:765] (3/8) Epoch 23, batch 2500, train_loss[loss=3.258, NarTop10Accuracy=0.675, over 5178.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7075, over 5468.04 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:35,038 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 19:39:37,631 INFO [trainer.py:765] (3/8) Epoch 24, batch 100, train_loss[loss=3.485, NarTop10Accuracy=0.6236, over 7413.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7024, over 2369.84 frames. ], batch size: 31, lr: 3.60e-03
2024-08-06 19:40:10,189 INFO [trainer.py:765] (3/8) Epoch 24, batch 200, train_loss[loss=2.85, NarTop10Accuracy=0.7483, over 6987.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 3860.05 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,555 INFO [trainer.py:765] (3/8) Epoch 24, batch 300, train_loss[loss=2.903, NarTop10Accuracy=0.7449, over 7251.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7078, over 4670.58 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,233 INFO [trainer.py:765] (3/8) Epoch 24, batch 400, train_loss[loss=3.08, NarTop10Accuracy=0.7146, over 5079.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7075, over 5113.99 frames. ], batch size: 7, lr: 3.59e-03
2024-08-06 19:41:50,322 INFO [trainer.py:765] (3/8) Epoch 24, batch 500, train_loss[loss=2.809, NarTop10Accuracy=0.7615, over 6174.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7092, over 5388.22 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,451 INFO [trainer.py:765] (3/8) Epoch 24, batch 600, train_loss[loss=2.887, NarTop10Accuracy=0.7576, over 5670.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7087, over 5651.30 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,843 INFO [trainer.py:765] (3/8) Epoch 24, batch 700, train_loss[loss=3.006, NarTop10Accuracy=0.7225, over 4989.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7074, over 5721.04 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,380 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (3/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:43:28,563 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.744e+02 2.113e+02 2.282e+02 2.472e+02 2.357e+03, threshold=4.564e+02, percent-clipped=0.2
2024-08-06 19:43:40,815 INFO [trainer.py:765] (3/8) Epoch 24, batch 800, train_loss[loss=2.883, NarTop10Accuracy=0.7453, over 5076.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7084, over 5771.88 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:44:11,410 INFO [trainer.py:765] (3/8) Epoch 24, batch 900, train_loss[loss=2.839, NarTop10Accuracy=0.7658, over 6267.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7074, over 5813.09 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:44:47,490 INFO [trainer.py:765] (3/8) Epoch 24, batch 1000, train_loss[loss=3.278, NarTop10Accuracy=0.6669, over 6282.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7048, over 5913.18 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:45:27,108 INFO [trainer.py:765] (3/8) Epoch 24, batch 1100, train_loss[loss=3.406, NarTop10Accuracy=0.6422, over 6879.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7029, over 5933.70 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,438 INFO [trainer.py:765] (3/8) Epoch 24, batch 1200, train_loss[loss=3.09, NarTop10Accuracy=0.711, over 7494.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.7044, over 5934.83 frames. ], batch size: 31, lr: 3.57e-03
2024-08-06 19:46:30,295 INFO [trainer.py:765] (3/8) Epoch 24, batch 1300, train_loss[loss=3.268, NarTop10Accuracy=0.6597, over 5076.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7064, over 5998.41 frames. ], batch size: 6, lr: 3.56e-03
2024-08-06 19:47:07,860 INFO [trainer.py:765] (3/8) Epoch 24, batch 1400, train_loss[loss=3.388, NarTop10Accuracy=0.6478, over 6204.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7033, over 6017.82 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,957 INFO [trainer.py:765] (3/8) Epoch 24, batch 1500, train_loss[loss=3.439, NarTop10Accuracy=0.6346, over 6222.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7007, over 5973.91 frames. ], batch size: 51, lr: 3.56e-03
2024-08-06 19:48:08,676 INFO [trainer.py:765] (3/8) Epoch 24, batch 1600, train_loss[loss=3.366, NarTop10Accuracy=0.6523, over 7167.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7001, over 5943.88 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,267 INFO [trainer.py:765] (3/8) Epoch 24, batch 1700, train_loss[loss=2.851, NarTop10Accuracy=0.7582, over 6543.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7001, over 5920.33 frames. ], batch size: 14, lr: 3.55e-03
2024-08-06 19:49:01,639 INFO [trainer.py:765] (3/8) Epoch 24, batch 1800, train_loss[loss=2.839, NarTop10Accuracy=0.764, over 7221.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6991, over 5984.30 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:49:28,042 INFO [trainer.py:765] (3/8) Epoch 24, batch 1900, train_loss[loss=3.497, NarTop10Accuracy=0.6252, over 6261.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6978, over 6018.33 frames. ], batch size: 53, lr: 3.55e-03
2024-08-06 19:49:53,534 INFO [trainer.py:765] (3/8) Epoch 24, batch 2000, train_loss[loss=3.553, NarTop10Accuracy=0.6149, over 6516.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7036, over 5991.32 frames. ], batch size: 52, lr: 3.54e-03
2024-08-06 19:50:18,820 INFO [trainer.py:765] (3/8) Epoch 24, batch 2100, train_loss[loss=2.815, NarTop10Accuracy=0.7705, over 4950.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7036, over 5971.84 frames. ], batch size: 5, lr: 3.54e-03
2024-08-06 19:50:43,942 INFO [trainer.py:765] (3/8) Epoch 24, batch 2200, train_loss[loss=3.49, NarTop10Accuracy=0.6277, over 7353.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.703, over 5999.53 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,025 INFO [trainer.py:765] (3/8) Epoch 24, batch 2300, train_loss[loss=2.843, NarTop10Accuracy=0.7626, over 5745.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7037, over 6015.71 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,349 INFO [trainer.py:765] (3/8) Epoch 24, batch 2400, train_loss[loss=2.973, NarTop10Accuracy=0.7168, over 5286.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7049, over 5782.64 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:51:56,783 INFO [trainer.py:765] (3/8) Epoch 24, batch 2500, train_loss[loss=2.99, NarTop10Accuracy=0.7333, over 5709.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7093, over 5493.99 frames. ], batch size: 8, lr: 3.53e-03
2024-08-06 19:52:16,695 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 19:53:22,199 INFO [trainer.py:765] (3/8) Epoch 25, batch 100, train_loss[loss=3.444, NarTop10Accuracy=0.6337, over 7488.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7084, over 2362.86 frames. ], batch size: 32, lr: 3.45e-03
2024-08-06 19:53:47,262 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (3/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,329 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.693e+02 2.155e+02 2.306e+02 2.475e+02 6.485e+02, threshold=4.611e+02, percent-clipped=0.1
2024-08-06 19:54:01,176 INFO [trainer.py:765] (3/8) Epoch 25, batch 200, train_loss[loss=2.908, NarTop10Accuracy=0.7587, over 6735.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.709, over 3850.93 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,646 INFO [trainer.py:765] (3/8) Epoch 25, batch 300, train_loss[loss=3.307, NarTop10Accuracy=0.6681, over 6927.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.711, over 4660.67 frames. ], batch size: 22, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (3/8) Epoch 25, batch 400, train_loss[loss=2.988, NarTop10Accuracy=0.726, over 5031.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7088, over 5125.77 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,737 INFO [trainer.py:765] (3/8) Epoch 25, batch 500, train_loss[loss=2.8, NarTop10Accuracy=0.7687, over 6021.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.711, over 5407.78 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,814 INFO [trainer.py:765] (3/8) Epoch 25, batch 600, train_loss[loss=2.84, NarTop10Accuracy=0.7617, over 5784.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7101, over 5659.35 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,496 INFO [trainer.py:765] (3/8) Epoch 25, batch 700, train_loss[loss=2.894, NarTop10Accuracy=0.7474, over 5130.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7104, over 5712.39 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:57:30,135 INFO [trainer.py:765] (3/8) Epoch 25, batch 800, train_loss[loss=3.006, NarTop10Accuracy=0.7246, over 4908.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7088, over 5767.69 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:58:00,678 INFO [trainer.py:765] (3/8) Epoch 25, batch 900, train_loss[loss=3.181, NarTop10Accuracy=0.6916, over 6297.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7097, over 5790.31 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:58:37,638 INFO [trainer.py:765] (3/8) Epoch 25, batch 1000, train_loss[loss=2.803, NarTop10Accuracy=0.7655, over 6684.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7069, over 5904.55 frames. ], batch size: 14, lr: 3.43e-03
2024-08-06 19:59:14,854 INFO [trainer.py:765] (3/8) Epoch 25, batch 1100, train_loss[loss=3.347, NarTop10Accuracy=0.6596, over 6771.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7065, over 5942.58 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,039 INFO [trainer.py:765] (3/8) Epoch 25, batch 1200, train_loss[loss=3.278, NarTop10Accuracy=0.6671, over 7392.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7056, over 5929.57 frames. ], batch size: 31, lr: 3.42e-03
2024-08-06 20:00:25,598 INFO [trainer.py:765] (3/8) Epoch 25, batch 1300, train_loss[loss=2.879, NarTop10Accuracy=0.7579, over 5109.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7075, over 5985.72 frames. ], batch size: 6, lr: 3.42e-03
2024-08-06 20:01:02,015 INFO [trainer.py:765] (3/8) Epoch 25, batch 1400, train_loss[loss=3.013, NarTop10Accuracy=0.7294, over 6045.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7099, over 5994.13 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,823 INFO [trainer.py:765] (3/8) Epoch 25, batch 1500, train_loss[loss=3.268, NarTop10Accuracy=0.6786, over 5928.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7091, over 5940.65 frames. ], batch size: 51, lr: 3.41e-03
2024-08-06 20:02:00,624 INFO [trainer.py:765] (3/8) Epoch 25, batch 1600, train_loss[loss=2.951, NarTop10Accuracy=0.7402, over 7284.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.71, over 5936.06 frames. ], batch size: 22, lr: 3.41e-03
2024-08-06 20:02:27,359 INFO [trainer.py:765] (3/8) Epoch 25, batch 1700, train_loss[loss=2.924, NarTop10Accuracy=0.7479, over 6180.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7106, over 5919.67 frames. ], batch size: 13, lr: 3.41e-03
2024-08-06 20:02:53,853 INFO [trainer.py:765] (3/8) Epoch 25, batch 1800, train_loss[loss=3.3, NarTop10Accuracy=0.6572, over 7092.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 5986.38 frames. ], batch size: 22, lr: 3.40e-03
2024-08-06 20:03:20,341 INFO [trainer.py:765] (3/8) Epoch 25, batch 1900, train_loss[loss=3.15, NarTop10Accuracy=0.6937, over 6213.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7044, over 6035.41 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:03:45,933 INFO [trainer.py:765] (3/8) Epoch 25, batch 2000, train_loss[loss=3.555, NarTop10Accuracy=0.6173, over 5937.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7027, over 6003.03 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:04:11,245 INFO [trainer.py:765] (3/8) Epoch 25, batch 2100, train_loss[loss=2.872, NarTop10Accuracy=0.7477, over 4011.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7043, over 5987.06 frames. ], batch size: 4, lr: 3.40e-03
2024-08-06 20:04:31,409 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:04:39,344 INFO [trainer.py:811] (3/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.755e+02 2.185e+02 2.339e+02 2.507e+02 3.640e+02, threshold=4.678e+02, percent-clipped=0.0
2024-08-06 20:04:44,513 INFO [trainer.py:765] (3/8) Epoch 25, batch 2200, train_loss[loss=3.313, NarTop10Accuracy=0.6623, over 7128.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7028, over 6024.53 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (3/8) Epoch 25, batch 2300, train_loss[loss=3.078, NarTop10Accuracy=0.7125, over 5583.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7025, over 6034.37 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (3/8) Epoch 25, batch 2400, train_loss[loss=2.81, NarTop10Accuracy=0.7701, over 5055.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7051, over 5764.50 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,846 INFO [trainer.py:765] (3/8) Epoch 25, batch 2500, train_loss[loss=2.819, NarTop10Accuracy=0.7648, over 5037.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7106, over 5477.67 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:06:17,585 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 20:07:19,305 INFO [trainer.py:765] (3/8) Epoch 26, batch 100, train_loss[loss=3.09, NarTop10Accuracy=0.711, over 7104.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7065, over 2361.05 frames. ], batch size: 31, lr: 3.32e-03
2024-08-06 20:07:52,382 INFO [trainer.py:765] (3/8) Epoch 26, batch 200, train_loss[loss=2.909, NarTop10Accuracy=0.7489, over 6807.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7058, over 3849.13 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,734 INFO [trainer.py:765] (3/8) Epoch 26, batch 300, train_loss[loss=2.975, NarTop10Accuracy=0.729, over 6882.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.707, over 4657.32 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,185 INFO [trainer.py:765] (3/8) Epoch 26, batch 400, train_loss[loss=2.979, NarTop10Accuracy=0.7288, over 5607.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7073, over 5128.73 frames. ], batch size: 8, lr: 3.31e-03
2024-08-06 20:09:33,148 INFO [trainer.py:765] (3/8) Epoch 26, batch 500, train_loss[loss=2.88, NarTop10Accuracy=0.7535, over 6075.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.706, over 5413.74 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,890 INFO [trainer.py:765] (3/8) Epoch 26, batch 600, train_loss[loss=2.842, NarTop10Accuracy=0.7612, over 5643.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7116, over 5669.91 frames. ], batch size: 9, lr: 3.30e-03
2024-08-06 20:10:39,873 INFO [trainer.py:765] (3/8) Epoch 26, batch 700, train_loss[loss=3.394, NarTop10Accuracy=0.643, over 5022.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7075, over 5731.18 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:19,061 INFO [trainer.py:765] (3/8) Epoch 26, batch 800, train_loss[loss=3.06, NarTop10Accuracy=0.7179, over 4350.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5790.35 frames. ], batch size: 5, lr: 3.30e-03
2024-08-06 20:11:49,316 INFO [trainer.py:765] (3/8) Epoch 26, batch 900, train_loss[loss=2.795, NarTop10Accuracy=0.7689, over 6675.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7087, over 5795.58 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:12:25,973 INFO [trainer.py:765] (3/8) Epoch 26, batch 1000, train_loss[loss=2.845, NarTop10Accuracy=0.758, over 6684.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.707, over 5882.85 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:13:06,377 INFO [trainer.py:765] (3/8) Epoch 26, batch 1100, train_loss[loss=3.303, NarTop10Accuracy=0.657, over 6870.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7043, over 5915.46 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,536 INFO [trainer.py:765] (3/8) Epoch 26, batch 1200, train_loss[loss=3.454, NarTop10Accuracy=0.6319, over 7389.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7069, over 5918.29 frames. ], batch size: 32, lr: 3.29e-03
2024-08-06 20:14:13,696 INFO [trainer.py:765] (3/8) Epoch 26, batch 1300, train_loss[loss=2.807, NarTop10Accuracy=0.7707, over 4230.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7075, over 5976.44 frames. ], batch size: 5, lr: 3.28e-03
2024-08-06 20:14:50,539 INFO [trainer.py:765] (3/8) Epoch 26, batch 1400, train_loss[loss=2.875, NarTop10Accuracy=0.7523, over 6174.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7068, over 5993.23 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,155 INFO [trainer.py:765] (3/8) Epoch 26, batch 1500, train_loss[loss=3.112, NarTop10Accuracy=0.7076, over 6630.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7069, over 5933.78 frames. ], batch size: 50, lr: 3.28e-03
2024-08-06 20:15:48,980 INFO [trainer.py:765] (3/8) Epoch 26, batch 1600, train_loss[loss=3.081, NarTop10Accuracy=0.7068, over 7056.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.709, over 5923.36 frames. ], batch size: 23, lr: 3.28e-03
2024-08-06 20:15:50,003 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:15:58,239 INFO [trainer.py:811] (3/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,239 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:15:58,779 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.752e+02 2.166e+02 2.322e+02 2.511e+02 3.952e+02, threshold=4.644e+02, percent-clipped=0.0
2024-08-06 20:16:23,951 INFO [trainer.py:765] (3/8) Epoch 26, batch 1700, train_loss[loss=3.141, NarTop10Accuracy=0.6973, over 6117.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7121, over 5929.17 frames. ], batch size: 13, lr: 3.28e-03
2024-08-06 20:16:50,426 INFO [trainer.py:765] (3/8) Epoch 26, batch 1800, train_loss[loss=2.887, NarTop10Accuracy=0.7556, over 7161.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7105, over 5966.11 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,839 INFO [trainer.py:765] (3/8) Epoch 26, batch 1900, train_loss[loss=2.982, NarTop10Accuracy=0.7379, over 6441.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 6009.18 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:17:42,379 INFO [trainer.py:765] (3/8) Epoch 26, batch 2000, train_loss[loss=3.598, NarTop10Accuracy=0.5979, over 6126.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.709, over 5979.54 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,562 INFO [trainer.py:765] (3/8) Epoch 26, batch 2100, train_loss[loss=3.032, NarTop10Accuracy=0.7097, over 4917.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.707, over 5972.84 frames. ], batch size: 5, lr: 3.27e-03
2024-08-06 20:18:32,776 INFO [trainer.py:765] (3/8) Epoch 26, batch 2200, train_loss[loss=2.858, NarTop10Accuracy=0.7577, over 7236.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7075, over 6013.49 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,897 INFO [trainer.py:765] (3/8) Epoch 26, batch 2300, train_loss[loss=3.207, NarTop10Accuracy=0.6822, over 5640.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7054, over 6035.17 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,205 INFO [trainer.py:765] (3/8) Epoch 26, batch 2400, train_loss[loss=2.788, NarTop10Accuracy=0.7739, over 5052.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7098, over 5782.27 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,651 INFO [trainer.py:765] (3/8) Epoch 26, batch 2500, train_loss[loss=2.746, NarTop10Accuracy=0.771, over 5178.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5468.01 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:06,170 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 20:21:04,874 INFO [trainer.py:765] (3/8) Epoch 27, batch 100, train_loss[loss=3.318, NarTop10Accuracy=0.6616, over 7407.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7099, over 2369.56 frames. ], batch size: 32, lr: 3.19e-03
2024-08-06 20:21:39,783 INFO [trainer.py:765] (3/8) Epoch 27, batch 200, train_loss[loss=2.771, NarTop10Accuracy=0.7748, over 6786.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7093, over 3833.75 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,050 INFO [trainer.py:765] (3/8) Epoch 27, batch 300, train_loss[loss=2.831, NarTop10Accuracy=0.7609, over 7023.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7081, over 4627.06 frames. ], batch size: 22, lr: 3.18e-03
2024-08-06 20:22:43,557 INFO [trainer.py:765] (3/8) Epoch 27, batch 400, train_loss[loss=2.933, NarTop10Accuracy=0.7326, over 5214.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7117, over 5078.45 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,084 INFO [trainer.py:765] (3/8) Epoch 27, batch 500, train_loss[loss=2.813, NarTop10Accuracy=0.7654, over 6135.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5350.59 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,435 INFO [trainer.py:765] (3/8) Epoch 27, batch 600, train_loss[loss=3.29, NarTop10Accuracy=0.6657, over 5676.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7144, over 5625.25 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,976 INFO [trainer.py:765] (3/8) Epoch 27, batch 700, train_loss[loss=2.661, NarTop10Accuracy=0.7856, over 4329.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.715, over 5704.31 frames. ], batch size: 5, lr: 3.18e-03
2024-08-06 20:25:03,408 INFO [trainer.py:765] (3/8) Epoch 27, batch 800, train_loss[loss=3.222, NarTop10Accuracy=0.6801, over 5085.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7116, over 5780.98 frames. ], batch size: 6, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (3/8) Epoch 27, batch 900, train_loss[loss=3.329, NarTop10Accuracy=0.6624, over 6510.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7106, over 5794.73 frames. ], batch size: 14, lr: 3.17e-03
2024-08-06 20:26:10,097 INFO [trainer.py:765] (3/8) Epoch 27, batch 1000, train_loss[loss=2.757, NarTop10Accuracy=0.783, over 6138.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7108, over 5895.55 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:18,315 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (3/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,346 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:26:26,877 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.789e+02 2.166e+02 2.331e+02 2.512e+02 4.284e+02, threshold=4.663e+02, percent-clipped=0.0
2024-08-06 20:26:50,899 INFO [trainer.py:765] (3/8) Epoch 27, batch 1100, train_loss[loss=3.068, NarTop10Accuracy=0.7093, over 6699.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.71, over 5919.27 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,544 INFO [trainer.py:765] (3/8) Epoch 27, batch 1200, train_loss[loss=2.99, NarTop10Accuracy=0.7313, over 7188.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7105, over 5922.16 frames. ], batch size: 31, lr: 3.16e-03
2024-08-06 20:27:58,568 INFO [trainer.py:765] (3/8) Epoch 27, batch 1300, train_loss[loss=2.969, NarTop10Accuracy=0.7277, over 5166.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.712, over 5993.11 frames. ], batch size: 6, lr: 3.16e-03
2024-08-06 20:28:36,745 INFO [trainer.py:765] (3/8) Epoch 27, batch 1400, train_loss[loss=3.557, NarTop10Accuracy=0.6177, over 5985.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 6011.22 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,632 INFO [trainer.py:765] (3/8) Epoch 27, batch 1500, train_loss[loss=3.008, NarTop10Accuracy=0.726, over 6456.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7104, over 5958.44 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,362 INFO [trainer.py:765] (3/8) Epoch 27, batch 1600, train_loss[loss=2.877, NarTop10Accuracy=0.7582, over 7092.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.709, over 5931.74 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:29:58,977 INFO [trainer.py:765] (3/8) Epoch 27, batch 1700, train_loss[loss=3.058, NarTop10Accuracy=0.7006, over 6774.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7095, over 5923.60 frames. ], batch size: 14, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (3/8) Epoch 27, batch 1800, train_loss[loss=3.481, NarTop10Accuracy=0.6287, over 7089.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7086, over 5982.92 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,845 INFO [trainer.py:765] (3/8) Epoch 27, batch 1900, train_loss[loss=3.142, NarTop10Accuracy=0.6911, over 6414.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7087, over 6013.23 frames. ], batch size: 51, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (3/8) Epoch 27, batch 2000, train_loss[loss=3.061, NarTop10Accuracy=0.7176, over 5754.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7109, over 6004.62 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:42,659 INFO [trainer.py:765] (3/8) Epoch 27, batch 2100, train_loss[loss=2.724, NarTop10Accuracy=0.7822, over 4830.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7097, over 5971.33 frames. ], batch size: 5, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (3/8) Epoch 27, batch 2200, train_loss[loss=3.499, NarTop10Accuracy=0.6271, over 7215.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.709, over 6013.39 frames. ], batch size: 31, lr: 3.14e-03
2024-08-06 20:32:32,941 INFO [trainer.py:765] (3/8) Epoch 27, batch 2300, train_loss[loss=2.86, NarTop10Accuracy=0.7492, over 5658.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 6014.83 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (3/8) Epoch 27, batch 2400, train_loss[loss=2.767, NarTop10Accuracy=0.783, over 5151.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7076, over 5781.36 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (3/8) Epoch 27, batch 2500, train_loss[loss=3.491, NarTop10Accuracy=0.6209, over 5286.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.714, over 5485.24 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,704 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 20:34:35,828 INFO [trainer.py:765] (3/8) Epoch 28, batch 100, train_loss[loss=2.903, NarTop10Accuracy=0.7488, over 7158.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7107, over 2364.74 frames. ], batch size: 32, lr: 3.07e-03
2024-08-06 20:35:07,393 INFO [trainer.py:765] (3/8) Epoch 28, batch 200, train_loss[loss=2.826, NarTop10Accuracy=0.7545, over 6918.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7112, over 3864.80 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,422 INFO [trainer.py:765] (3/8) Epoch 28, batch 300, train_loss[loss=3.082, NarTop10Accuracy=0.7067, over 6966.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7109, over 4662.82 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,864 INFO [trainer.py:765] (3/8) Epoch 28, batch 400, train_loss[loss=3.31, NarTop10Accuracy=0.669, over 5040.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7083, over 5099.96 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,406 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (3/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:36:41,102 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.761e+02 2.179e+02 2.348e+02 2.536e+02 3.573e+02, threshold=4.696e+02, percent-clipped=0.0
2024-08-06 20:36:56,663 INFO [trainer.py:765] (3/8) Epoch 28, batch 500, train_loss[loss=3.204, NarTop10Accuracy=0.6858, over 6138.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7105, over 5377.03 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,462 INFO [trainer.py:765] (3/8) Epoch 28, batch 600, train_loss[loss=3.057, NarTop10Accuracy=0.7114, over 5784.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7092, over 5645.78 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,891 INFO [trainer.py:765] (3/8) Epoch 28, batch 700, train_loss[loss=3.124, NarTop10Accuracy=0.7081, over 5043.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7079, over 5707.51 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,488 INFO [trainer.py:765] (3/8) Epoch 28, batch 800, train_loss[loss=2.811, NarTop10Accuracy=0.765, over 4992.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7147, over 5767.84 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:39:15,506 INFO [trainer.py:765] (3/8) Epoch 28, batch 900, train_loss[loss=3.336, NarTop10Accuracy=0.6574, over 6714.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7141, over 5791.61 frames. ], batch size: 14, lr: 3.06e-03
2024-08-06 20:39:53,239 INFO [trainer.py:765] (3/8) Epoch 28, batch 1000, train_loss[loss=3.232, NarTop10Accuracy=0.6759, over 6585.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7129, over 5909.31 frames. ], batch size: 14, lr: 3.05e-03
2024-08-06 20:40:25,867 INFO [trainer.py:765] (3/8) Epoch 28, batch 1100, train_loss[loss=2.844, NarTop10Accuracy=0.76, over 6741.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7099, over 5949.42 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,418 INFO [trainer.py:765] (3/8) Epoch 28, batch 1200, train_loss[loss=3.361, NarTop10Accuracy=0.6568, over 7101.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7092, over 5947.15 frames. ], batch size: 31, lr: 3.05e-03
2024-08-06 20:41:38,680 INFO [trainer.py:765] (3/8) Epoch 28, batch 1300, train_loss[loss=3.322, NarTop10Accuracy=0.66, over 5085.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7096, over 6003.18 frames. ], batch size: 6, lr: 3.05e-03
2024-08-06 20:42:13,047 INFO [trainer.py:765] (3/8) Epoch 28, batch 1400, train_loss[loss=2.934, NarTop10Accuracy=0.7471, over 6048.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 6013.45 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,171 INFO [trainer.py:765] (3/8) Epoch 28, batch 1500, train_loss[loss=3.356, NarTop10Accuracy=0.6472, over 5946.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7102, over 5955.23 frames. ], batch size: 51, lr: 3.04e-03
2024-08-06 20:43:11,080 INFO [trainer.py:765] (3/8) Epoch 28, batch 1600, train_loss[loss=2.965, NarTop10Accuracy=0.7365, over 7086.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 5929.50 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:43:37,785 INFO [trainer.py:765] (3/8) Epoch 28, batch 1700, train_loss[loss=2.982, NarTop10Accuracy=0.7231, over 6369.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.709, over 5909.51 frames. ], batch size: 13, lr: 3.04e-03
2024-08-06 20:44:04,325 INFO [trainer.py:765] (3/8) Epoch 28, batch 1800, train_loss[loss=2.987, NarTop10Accuracy=0.7325, over 7281.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7096, over 5970.77 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,757 INFO [trainer.py:765] (3/8) Epoch 28, batch 1900, train_loss[loss=3.137, NarTop10Accuracy=0.704, over 6375.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7112, over 6017.99 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:44:56,328 INFO [trainer.py:765] (3/8) Epoch 28, batch 2000, train_loss[loss=3.024, NarTop10Accuracy=0.7219, over 6072.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7142, over 6001.41 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:45:21,650 INFO [trainer.py:765] (3/8) Epoch 28, batch 2100, train_loss[loss=2.88, NarTop10Accuracy=0.7402, over 3921.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7151, over 5966.17 frames. ], batch size: 4, lr: 3.03e-03
2024-08-06 20:45:47,076 INFO [trainer.py:765] (3/8) Epoch 28, batch 2200, train_loss[loss=2.981, NarTop10Accuracy=0.7332, over 7350.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7123, over 6027.50 frames. ], batch size: 32, lr: 3.03e-03
2024-08-06 20:46:12,307 INFO [trainer.py:765] (3/8) Epoch 28, batch 2300, train_loss[loss=3.429, NarTop10Accuracy=0.6401, over 5850.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7076, over 6021.47 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,807 INFO [trainer.py:765] (3/8) Epoch 28, batch 2400, train_loss[loss=3.025, NarTop10Accuracy=0.7244, over 5244.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7065, over 5790.52 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,594 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (3/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:46:57,081 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.745e+02 2.201e+02 2.381e+02 2.551e+02 4.872e+02, threshold=4.762e+02, percent-clipped=0.1
2024-08-06 20:47:08,292 INFO [trainer.py:765] (3/8) Epoch 28, batch 2500, train_loss[loss=3.013, NarTop10Accuracy=0.7302, over 5163.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7108, over 5492.31 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,112 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 20:48:21,052 INFO [trainer.py:765] (3/8) Epoch 29, batch 100, train_loss[loss=2.937, NarTop10Accuracy=0.7386, over 6942.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7107, over 2367.96 frames. ], batch size: 31, lr: 2.96e-03
2024-08-06 20:48:53,405 INFO [trainer.py:765] (3/8) Epoch 29, batch 200, train_loss[loss=3.38, NarTop10Accuracy=0.6551, over 6825.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.717, over 3850.00 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,476 INFO [trainer.py:765] (3/8) Epoch 29, batch 300, train_loss[loss=3.161, NarTop10Accuracy=0.6886, over 7155.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.718, over 4636.33 frames. ], batch size: 22, lr: 2.96e-03
2024-08-06 20:49:56,052 INFO [trainer.py:765] (3/8) Epoch 29, batch 400, train_loss[loss=3.359, NarTop10Accuracy=0.6518, over 5106.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7142, over 5090.86 frames. ], batch size: 7, lr: 2.96e-03
2024-08-06 20:50:29,435 INFO [trainer.py:765] (3/8) Epoch 29, batch 500, train_loss[loss=3.037, NarTop10Accuracy=0.7076, over 6126.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 5384.93 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,024 INFO [trainer.py:765] (3/8) Epoch 29, batch 600, train_loss[loss=2.722, NarTop10Accuracy=0.7773, over 5829.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7157, over 5654.54 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,677 INFO [trainer.py:765] (3/8) Epoch 29, batch 700, train_loss[loss=2.973, NarTop10Accuracy=0.7256, over 5151.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7107, over 5730.36 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:10,724 INFO [trainer.py:765] (3/8) Epoch 29, batch 800, train_loss[loss=2.636, NarTop10Accuracy=0.8067, over 4314.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7117, over 5760.30 frames. ], batch size: 5, lr: 2.95e-03
2024-08-06 20:52:40,743 INFO [trainer.py:765] (3/8) Epoch 29, batch 900, train_loss[loss=2.714, NarTop10Accuracy=0.7883, over 6324.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7107, over 5802.04 frames. ], batch size: 13, lr: 2.95e-03
2024-08-06 20:53:16,861 INFO [trainer.py:765] (3/8) Epoch 29, batch 1000, train_loss[loss=3.445, NarTop10Accuracy=0.6348, over 6594.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 5894.71 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:52,902 INFO [trainer.py:765] (3/8) Epoch 29, batch 1100, train_loss[loss=3.126, NarTop10Accuracy=0.7055, over 6720.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7085, over 5927.13 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,689 INFO [trainer.py:765] (3/8) Epoch 29, batch 1200, train_loss[loss=3.26, NarTop10Accuracy=0.6707, over 6909.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 5933.52 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,427 INFO [trainer.py:765] (3/8) Epoch 29, batch 1300, train_loss[loss=2.836, NarTop10Accuracy=0.7545, over 4257.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7108, over 5986.95 frames. ], batch size: 5, lr: 2.94e-03
2024-08-06 20:55:32,556 INFO [trainer.py:765] (3/8) Epoch 29, batch 1400, train_loss[loss=3.373, NarTop10Accuracy=0.6548, over 6108.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 6004.12 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,358 INFO [trainer.py:765] (3/8) Epoch 29, batch 1500, train_loss[loss=3.406, NarTop10Accuracy=0.6448, over 6102.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 5951.88 frames. ], batch size: 51, lr: 2.94e-03
2024-08-06 20:56:32,040 INFO [trainer.py:765] (3/8) Epoch 29, batch 1600, train_loss[loss=3.383, NarTop10Accuracy=0.6544, over 7092.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.709, over 5950.56 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,638 INFO [trainer.py:765] (3/8) Epoch 29, batch 1700, train_loss[loss=2.732, NarTop10Accuracy=0.7787, over 6567.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7104, over 5924.40 frames. ], batch size: 14, lr: 2.93e-03
2024-08-06 20:57:24,999 INFO [trainer.py:765] (3/8) Epoch 29, batch 1800, train_loss[loss=3.039, NarTop10Accuracy=0.714, over 6972.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7119, over 5984.43 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,620 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (3/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.772e+02 2.206e+02 2.380e+02 2.554e+02 4.464e+02, threshold=4.759e+02, percent-clipped=0.0
2024-08-06 20:57:59,757 INFO [trainer.py:765] (3/8) Epoch 29, batch 1900, train_loss[loss=2.986, NarTop10Accuracy=0.7327, over 5478.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7078, over 6030.11 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:25,309 INFO [trainer.py:765] (3/8) Epoch 29, batch 2000, train_loss[loss=3.491, NarTop10Accuracy=0.624, over 6447.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 6007.87 frames. ], batch size: 51, lr: 2.93e-03
2024-08-06 20:58:50,630 INFO [trainer.py:765] (3/8) Epoch 29, batch 2100, train_loss[loss=2.913, NarTop10Accuracy=0.7424, over 3924.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7092, over 5969.67 frames. ], batch size: 4, lr: 2.92e-03
2024-08-06 20:59:15,806 INFO [trainer.py:765] (3/8) Epoch 29, batch 2200, train_loss[loss=2.838, NarTop10Accuracy=0.7604, over 6948.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7103, over 6006.90 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,911 INFO [trainer.py:765] (3/8) Epoch 29, batch 2300, train_loss[loss=2.898, NarTop10Accuracy=0.7462, over 5796.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7068, over 6032.80 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,156 INFO [trainer.py:765] (3/8) Epoch 29, batch 2400, train_loss[loss=2.701, NarTop10Accuracy=0.7864, over 5205.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7095, over 5768.41 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,742 INFO [trainer.py:765] (3/8) Epoch 29, batch 2500, train_loss[loss=3.513, NarTop10Accuracy=0.627, over 5112.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7147, over 5453.74 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:48,499 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 21:01:41,717 INFO [trainer.py:765] (3/8) Epoch 30, batch 100, train_loss[loss=2.855, NarTop10Accuracy=0.7498, over 7551.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7211, over 2360.64 frames. ], batch size: 32, lr: 2.86e-03
2024-08-06 21:02:17,015 INFO [trainer.py:765] (3/8) Epoch 30, batch 200, train_loss[loss=2.791, NarTop10Accuracy=0.767, over 6798.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.723, over 3843.57 frames. ], batch size: 17, lr: 2.86e-03
2024-08-06 21:02:51,343 INFO [trainer.py:765] (3/8) Epoch 30, batch 300, train_loss[loss=2.947, NarTop10Accuracy=0.7362, over 7137.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7246, over 4649.71 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,643 INFO [trainer.py:765] (3/8) Epoch 30, batch 400, train_loss[loss=2.703, NarTop10Accuracy=0.7809, over 5049.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7197, over 5090.84 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,546 INFO [trainer.py:765] (3/8) Epoch 30, batch 500, train_loss[loss=3.371, NarTop10Accuracy=0.6534, over 6093.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 5391.83 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,658 INFO [trainer.py:765] (3/8) Epoch 30, batch 600, train_loss[loss=2.875, NarTop10Accuracy=0.7455, over 5679.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7162, over 5668.94 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,526 INFO [trainer.py:765] (3/8) Epoch 30, batch 700, train_loss[loss=2.919, NarTop10Accuracy=0.7404, over 5106.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7192, over 5748.87 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:05:44,132 INFO [trainer.py:765] (3/8) Epoch 30, batch 800, train_loss[loss=2.966, NarTop10Accuracy=0.7288, over 5103.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7195, over 5806.89 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:06:14,844 INFO [trainer.py:765] (3/8) Epoch 30, batch 900, train_loss[loss=2.881, NarTop10Accuracy=0.7532, over 6231.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7186, over 5790.92 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:06:48,952 INFO [trainer.py:765] (3/8) Epoch 30, batch 1000, train_loss[loss=2.97, NarTop10Accuracy=0.7356, over 6666.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7126, over 5907.62 frames. ], batch size: 14, lr: 2.85e-03
2024-08-06 21:07:25,937 INFO [trainer.py:765] (3/8) Epoch 30, batch 1100, train_loss[loss=3.389, NarTop10Accuracy=0.6387, over 6747.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7097, over 5926.48 frames. ], batch size: 17, lr: 2.84e-03
2024-08-06 21:08:02,381 INFO [trainer.py:765] (3/8) Epoch 30, batch 1200, train_loss[loss=2.895, NarTop10Accuracy=0.7464, over 7401.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7121, over 5917.38 frames. ], batch size: 31, lr: 2.84e-03
2024-08-06 21:08:35,371 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (3/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,458 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 21:08:44,198 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.770e+02 2.209e+02 2.377e+02 2.553e+02 3.956e+02, threshold=4.754e+02, percent-clipped=0.0
2024-08-06 21:08:44,203 INFO [trainer.py:765] (3/8) Epoch 30, batch 1300, train_loss[loss=3.335, NarTop10Accuracy=0.6647, over 4299.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 5976.26 frames. ], batch size: 5, lr: 2.84e-03
2024-08-06 21:09:22,398 INFO [trainer.py:765] (3/8) Epoch 30, batch 1400, train_loss[loss=2.857, NarTop10Accuracy=0.7454, over 6093.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7118, over 6002.92 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,372 INFO [trainer.py:765] (3/8) Epoch 30, batch 1500, train_loss[loss=3.04, NarTop10Accuracy=0.7219, over 6684.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7124, over 5941.78 frames. ], batch size: 50, lr: 2.84e-03
2024-08-06 21:10:20,083 INFO [trainer.py:765] (3/8) Epoch 30, batch 1600, train_loss[loss=3.076, NarTop10Accuracy=0.7081, over 6951.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.712, over 5929.47 frames. ], batch size: 22, lr: 2.84e-03
2024-08-06 21:10:46,678 INFO [trainer.py:765] (3/8) Epoch 30, batch 1700, train_loss[loss=3.032, NarTop10Accuracy=0.7122, over 6216.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7114, over 5922.01 frames. ], batch size: 13, lr: 2.83e-03
2024-08-06 21:11:13,058 INFO [trainer.py:765] (3/8) Epoch 30, batch 1800, train_loss[loss=3.51, NarTop10Accuracy=0.6198, over 7095.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7106, over 5977.62 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,418 INFO [trainer.py:765] (3/8) Epoch 30, batch 1900, train_loss[loss=3.085, NarTop10Accuracy=0.7118, over 6552.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 6036.69 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:04,826 INFO [trainer.py:765] (3/8) Epoch 30, batch 2000, train_loss[loss=3.361, NarTop10Accuracy=0.6489, over 5718.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 5982.96 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:30,088 INFO [trainer.py:765] (3/8) Epoch 30, batch 2100, train_loss[loss=2.93, NarTop10Accuracy=0.7305, over 3891.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5969.57 frames. ], batch size: 4, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (3/8) Epoch 30, batch 2200, train_loss[loss=2.979, NarTop10Accuracy=0.7309, over 7350.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.711, over 6005.77 frames. ], batch size: 31, lr: 2.82e-03
2024-08-06 21:13:20,296 INFO [trainer.py:765] (3/8) Epoch 30, batch 2300, train_loss[loss=2.757, NarTop10Accuracy=0.7693, over 5754.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7071, over 6024.98 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,491 INFO [trainer.py:765] (3/8) Epoch 30, batch 2400, train_loss[loss=2.905, NarTop10Accuracy=0.7616, over 5157.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7148, over 5794.32 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,987 INFO [trainer.py:765] (3/8) Epoch 30, batch 2500, train_loss[loss=2.985, NarTop10Accuracy=0.7333, over 5283.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7164, over 5473.88 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,770 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 21:15:23,632 INFO [trainer.py:765] (3/8) Epoch 31, batch 100, train_loss[loss=3.417, NarTop10Accuracy=0.6378, over 7092.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.713, over 2361.72 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,127 INFO [trainer.py:765] (3/8) Epoch 31, batch 200, train_loss[loss=2.93, NarTop10Accuracy=0.7455, over 6867.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7182, over 3861.68 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,215 INFO [trainer.py:765] (3/8) Epoch 31, batch 300, train_loss[loss=3.013, NarTop10Accuracy=0.7321, over 7284.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7183, over 4684.30 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,625 INFO [trainer.py:765] (3/8) Epoch 31, batch 400, train_loss[loss=3.39, NarTop10Accuracy=0.6506, over 5238.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7147, over 5131.93 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,724 INFO [trainer.py:765] (3/8) Epoch 31, batch 500, train_loss[loss=2.812, NarTop10Accuracy=0.7583, over 6171.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7167, over 5406.19 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,084 INFO [trainer.py:765] (3/8) Epoch 31, batch 600, train_loss[loss=2.643, NarTop10Accuracy=0.7997, over 5709.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7142, over 5658.07 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,609 INFO [trainer.py:765] (3/8) Epoch 31, batch 700, train_loss[loss=3.214, NarTop10Accuracy=0.6772, over 5064.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5736.77 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:18:51,094 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (3/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,276 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 21:18:59,986 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.824e+02 2.222e+02 2.378e+02 2.557e+02 4.306e+02, threshold=4.755e+02, percent-clipped=0.0
2024-08-06 21:19:24,245 INFO [trainer.py:765] (3/8) Epoch 31, batch 800, train_loss[loss=2.646, NarTop10Accuracy=0.7929, over 4932.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7152, over 5786.21 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:19:56,950 INFO [trainer.py:765] (3/8) Epoch 31, batch 900, train_loss[loss=3.415, NarTop10Accuracy=0.6453, over 6240.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7157, over 5796.23 frames. ], batch size: 13, lr: 2.76e-03
2024-08-06 21:20:33,310 INFO [trainer.py:765] (3/8) Epoch 31, batch 1000, train_loss[loss=3.432, NarTop10Accuracy=0.6329, over 6141.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7158, over 5887.74 frames. ], batch size: 13, lr: 2.75e-03
2024-08-06 21:21:10,215 INFO [trainer.py:765] (3/8) Epoch 31, batch 1100, train_loss[loss=3.231, NarTop10Accuracy=0.682, over 6681.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 5926.49 frames. ], batch size: 17, lr: 2.75e-03
2024-08-06 21:21:41,118 INFO [trainer.py:765] (3/8) Epoch 31, batch 1200, train_loss[loss=2.932, NarTop10Accuracy=0.7406, over 7287.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5905.92 frames. ], batch size: 31, lr: 2.75e-03
2024-08-06 21:22:19,741 INFO [trainer.py:765] (3/8) Epoch 31, batch 1300, train_loss[loss=2.901, NarTop10Accuracy=0.7496, over 5052.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7124, over 5983.62 frames. ], batch size: 6, lr: 2.75e-03
2024-08-06 21:22:53,533 INFO [trainer.py:765] (3/8) Epoch 31, batch 1400, train_loss[loss=2.876, NarTop10Accuracy=0.7462, over 6159.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7107, over 6013.83 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,269 INFO [trainer.py:765] (3/8) Epoch 31, batch 1500, train_loss[loss=3.344, NarTop10Accuracy=0.6599, over 6234.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7142, over 5951.40 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:23:49,004 INFO [trainer.py:765] (3/8) Epoch 31, batch 1600, train_loss[loss=3.369, NarTop10Accuracy=0.6478, over 7155.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5931.60 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,511 INFO [trainer.py:765] (3/8) Epoch 31, batch 1700, train_loss[loss=3.433, NarTop10Accuracy=0.6337, over 6606.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.714, over 5910.24 frames. ], batch size: 14, lr: 2.74e-03
2024-08-06 21:24:41,995 INFO [trainer.py:765] (3/8) Epoch 31, batch 1800, train_loss[loss=2.887, NarTop10Accuracy=0.7479, over 7080.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 5981.96 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:25:08,356 INFO [trainer.py:765] (3/8) Epoch 31, batch 1900, train_loss[loss=3.286, NarTop10Accuracy=0.6695, over 6060.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7127, over 6034.13 frames. ], batch size: 52, lr: 2.74e-03
2024-08-06 21:25:33,772 INFO [trainer.py:765] (3/8) Epoch 31, batch 2000, train_loss[loss=3.018, NarTop10Accuracy=0.7265, over 5685.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7137, over 6008.82 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:59,106 INFO [trainer.py:765] (3/8) Epoch 31, batch 2100, train_loss[loss=2.677, NarTop10Accuracy=0.7788, over 4878.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7146, over 5981.22 frames. ], batch size: 5, lr: 2.73e-03
2024-08-06 21:26:24,237 INFO [trainer.py:765] (3/8) Epoch 31, batch 2200, train_loss[loss=2.976, NarTop10Accuracy=0.7299, over 7113.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7169, over 6008.32 frames. ], batch size: 31, lr: 2.73e-03
2024-08-06 21:26:49,321 INFO [trainer.py:765] (3/8) Epoch 31, batch 2300, train_loss[loss=2.762, NarTop10Accuracy=0.7719, over 5607.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7143, over 6013.79 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,607 INFO [trainer.py:765] (3/8) Epoch 31, batch 2400, train_loss[loss=2.85, NarTop10Accuracy=0.7605, over 5115.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5776.50 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,027 INFO [trainer.py:765] (3/8) Epoch 31, batch 2500, train_loss[loss=2.836, NarTop10Accuracy=0.7554, over 5067.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7166, over 5484.81 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:57,049 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 21:28:49,393 INFO [trainer.py:765] (3/8) Epoch 32, batch 100, train_loss[loss=2.908, NarTop10Accuracy=0.7438, over 7341.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7132, over 2369.47 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,161 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (3/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 21:29:16,939 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.842e+02 2.253e+02 2.413e+02 2.600e+02 5.680e+02, threshold=4.826e+02, percent-clipped=0.1
2024-08-06 21:29:32,272 INFO [trainer.py:765] (3/8) Epoch 32, batch 200, train_loss[loss=3.286, NarTop10Accuracy=0.6734, over 6699.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7126, over 3864.95 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,278 INFO [trainer.py:765] (3/8) Epoch 32, batch 300, train_loss[loss=3.034, NarTop10Accuracy=0.7196, over 7098.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7145, over 4653.46 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,103 INFO [trainer.py:765] (3/8) Epoch 32, batch 400, train_loss[loss=2.83, NarTop10Accuracy=0.7579, over 5103.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7113, over 5105.33 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,530 INFO [trainer.py:765] (3/8) Epoch 32, batch 500, train_loss[loss=3.016, NarTop10Accuracy=0.7242, over 6150.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.714, over 5374.89 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,486 INFO [trainer.py:765] (3/8) Epoch 32, batch 600, train_loss[loss=3.204, NarTop10Accuracy=0.6781, over 5712.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7147, over 5637.35 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,028 INFO [trainer.py:765] (3/8) Epoch 32, batch 700, train_loss[loss=2.833, NarTop10Accuracy=0.7585, over 4203.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7167, over 5705.64 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:00,646 INFO [trainer.py:765] (3/8) Epoch 32, batch 800, train_loss[loss=3.178, NarTop10Accuracy=0.6794, over 4917.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7165, over 5765.19 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:28,991 INFO [trainer.py:765] (3/8) Epoch 32, batch 900, train_loss[loss=2.851, NarTop10Accuracy=0.7526, over 6267.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7188, over 5785.78 frames. ], batch size: 13, lr: 2.67e-03
2024-08-06 21:34:04,049 INFO [trainer.py:765] (3/8) Epoch 32, batch 1000, train_loss[loss=3.221, NarTop10Accuracy=0.6812, over 6546.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7171, over 5888.33 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:46,674 INFO [trainer.py:765] (3/8) Epoch 32, batch 1100, train_loss[loss=3.24, NarTop10Accuracy=0.6771, over 6771.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7156, over 5935.38 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,171 INFO [trainer.py:765] (3/8) Epoch 32, batch 1200, train_loss[loss=3.194, NarTop10Accuracy=0.6836, over 7239.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7147, over 5915.38 frames. ], batch size: 31, lr: 2.66e-03
2024-08-06 21:35:52,800 INFO [trainer.py:765] (3/8) Epoch 32, batch 1300, train_loss[loss=3.235, NarTop10Accuracy=0.6801, over 5013.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7146, over 5982.23 frames. ], batch size: 6, lr: 2.66e-03
2024-08-06 21:36:29,478 INFO [trainer.py:765] (3/8) Epoch 32, batch 1400, train_loss[loss=3.328, NarTop10Accuracy=0.647, over 6072.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 6008.34 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,733 INFO [trainer.py:765] (3/8) Epoch 32, batch 1500, train_loss[loss=3.453, NarTop10Accuracy=0.638, over 5919.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.714, over 5952.38 frames. ], batch size: 50, lr: 2.66e-03
2024-08-06 21:37:32,521 INFO [trainer.py:765] (3/8) Epoch 32, batch 1600, train_loss[loss=3.006, NarTop10Accuracy=0.7266, over 7383.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7149, over 5929.47 frames. ], batch size: 23, lr: 2.66e-03
2024-08-06 21:37:59,159 INFO [trainer.py:765] (3/8) Epoch 32, batch 1700, train_loss[loss=3.033, NarTop10Accuracy=0.7161, over 6681.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7159, over 5923.32 frames. ], batch size: 14, lr: 2.65e-03
2024-08-06 21:38:25,702 INFO [trainer.py:765] (3/8) Epoch 32, batch 1800, train_loss[loss=3.097, NarTop10Accuracy=0.7073, over 7050.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 5992.44 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,168 INFO [trainer.py:765] (3/8) Epoch 32, batch 1900, train_loss[loss=3.08, NarTop10Accuracy=0.7097, over 6192.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7107, over 6021.10 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:17,768 INFO [trainer.py:765] (3/8) Epoch 32, batch 2000, train_loss[loss=3.481, NarTop10Accuracy=0.6273, over 6060.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7127, over 5988.00 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:43,178 INFO [trainer.py:765] (3/8) Epoch 32, batch 2100, train_loss[loss=2.696, NarTop10Accuracy=0.7785, over 3957.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 5964.62 frames. ], batch size: 4, lr: 2.65e-03
2024-08-06 21:39:54,781 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 21:40:02,942 INFO [trainer.py:811] (3/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.874e+02 2.278e+02 2.449e+02 2.609e+02 8.207e+02, threshold=4.898e+02, percent-clipped=0.3
2024-08-06 21:40:16,628 INFO [trainer.py:765] (3/8) Epoch 32, batch 2200, train_loss[loss=3.148, NarTop10Accuracy=0.698, over 7320.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7137, over 6005.61 frames. ], batch size: 31, lr: 2.65e-03
2024-08-06 21:40:41,717 INFO [trainer.py:765] (3/8) Epoch 32, batch 2300, train_loss[loss=3.284, NarTop10Accuracy=0.673, over 5706.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7092, over 6009.44 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,072 INFO [trainer.py:765] (3/8) Epoch 32, batch 2400, train_loss[loss=3.176, NarTop10Accuracy=0.6897, over 5172.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7128, over 5773.38 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,537 INFO [trainer.py:765] (3/8) Epoch 32, batch 2500, train_loss[loss=2.888, NarTop10Accuracy=0.7554, over 5016.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7194, over 5483.78 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,758 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 21:42:47,615 INFO [trainer.py:765] (3/8) Epoch 33, batch 100, train_loss[loss=2.97, NarTop10Accuracy=0.7325, over 7131.00 frames. ], tot_loss[loss=2.998, NarTop10Accuracy=0.726, over 2356.74 frames. ], batch size: 31, lr: 2.60e-03
2024-08-06 21:43:22,367 INFO [trainer.py:765] (3/8) Epoch 33, batch 200, train_loss[loss=2.764, NarTop10Accuracy=0.7649, over 6792.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 3857.76 frames. ], batch size: 17, lr: 2.60e-03
2024-08-06 21:43:56,512 INFO [trainer.py:765] (3/8) Epoch 33, batch 300, train_loss[loss=3.344, NarTop10Accuracy=0.6547, over 7206.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.717, over 4656.21 frames. ], batch size: 23, lr: 2.60e-03
2024-08-06 21:44:30,316 INFO [trainer.py:765] (3/8) Epoch 33, batch 400, train_loss[loss=2.704, NarTop10Accuracy=0.7865, over 5121.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7172, over 5109.34 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,869 INFO [trainer.py:765] (3/8) Epoch 33, batch 500, train_loss[loss=2.648, NarTop10Accuracy=0.7939, over 6162.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7208, over 5391.70 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,226 INFO [trainer.py:765] (3/8) Epoch 33, batch 600, train_loss[loss=3.52, NarTop10Accuracy=0.6273, over 5721.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7146, over 5659.13 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,316 INFO [trainer.py:765] (3/8) Epoch 33, batch 700, train_loss[loss=2.758, NarTop10Accuracy=0.7699, over 5097.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7144, over 5712.84 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (3/8) Epoch 33, batch 800, train_loss[loss=2.699, NarTop10Accuracy=0.7868, over 4947.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7156, over 5780.59 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:47:18,907 INFO [trainer.py:765] (3/8) Epoch 33, batch 900, train_loss[loss=3.192, NarTop10Accuracy=0.6882, over 6300.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.715, over 5819.60 frames. ], batch size: 13, lr: 2.59e-03
2024-08-06 21:47:57,315 INFO [trainer.py:765] (3/8) Epoch 33, batch 1000, train_loss[loss=2.803, NarTop10Accuracy=0.7604, over 6210.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7145, over 5906.58 frames. ], batch size: 13, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (3/8) Epoch 33, batch 1100, train_loss[loss=2.778, NarTop10Accuracy=0.7605, over 6753.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7112, over 5943.00 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,659 INFO [trainer.py:765] (3/8) Epoch 33, batch 1200, train_loss[loss=2.795, NarTop10Accuracy=0.7676, over 7170.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.713, over 5927.83 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,815 INFO [trainer.py:765] (3/8) Epoch 33, batch 1300, train_loss[loss=2.913, NarTop10Accuracy=0.7439, over 4323.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7151, over 5987.56 frames. ], batch size: 5, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (3/8) Epoch 33, batch 1400, train_loss[loss=3.228, NarTop10Accuracy=0.6741, over 6120.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7136, over 6010.01 frames. ], batch size: 11, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (3/8) Epoch 33, batch 1500, train_loss[loss=3.1, NarTop10Accuracy=0.704, over 6021.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.715, over 5944.83 frames. ], batch size: 50, lr: 2.58e-03
2024-08-06 21:51:04,607 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 21:51:12,661 INFO [trainer.py:811] (3/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 21:51:13,181 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.834e+02 2.250e+02 2.409e+02 2.586e+02 3.975e+02, threshold=4.818e+02, percent-clipped=0.0
2024-08-06 21:51:21,261 INFO [trainer.py:765] (3/8) Epoch 33, batch 1600, train_loss[loss=3.151, NarTop10Accuracy=0.6961, over 7104.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7165, over 5929.91 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,923 INFO [trainer.py:765] (3/8) Epoch 33, batch 1700, train_loss[loss=2.795, NarTop10Accuracy=0.765, over 6519.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7141, over 5921.31 frames. ], batch size: 14, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (3/8) Epoch 33, batch 1800, train_loss[loss=2.812, NarTop10Accuracy=0.7637, over 7164.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7166, over 5994.43 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,856 INFO [trainer.py:765] (3/8) Epoch 33, batch 1900, train_loss[loss=3.375, NarTop10Accuracy=0.6436, over 6849.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7124, over 6035.06 frames. ], batch size: 51, lr: 2.57e-03
2024-08-06 21:53:06,353 INFO [trainer.py:765] (3/8) Epoch 33, batch 2000, train_loss[loss=3.444, NarTop10Accuracy=0.6278, over 5583.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7166, over 6015.67 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:31,659 INFO [trainer.py:765] (3/8) Epoch 33, batch 2100, train_loss[loss=3.467, NarTop10Accuracy=0.6335, over 4683.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7155, over 5994.96 frames. ], batch size: 5, lr: 2.57e-03
2024-08-06 21:53:56,891 INFO [trainer.py:765] (3/8) Epoch 33, batch 2200, train_loss[loss=3.399, NarTop10Accuracy=0.6471, over 7290.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.714, over 6020.72 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (3/8) Epoch 33, batch 2300, train_loss[loss=2.638, NarTop10Accuracy=0.7976, over 5751.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7149, over 6022.08 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,430 INFO [trainer.py:765] (3/8) Epoch 33, batch 2400, train_loss[loss=2.829, NarTop10Accuracy=0.7535, over 5127.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7176, over 5783.21 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (3/8) Epoch 33, batch 2500, train_loss[loss=2.727, NarTop10Accuracy=0.785, over 5124.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7221, over 5489.68 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,643 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 21:56:24,721 INFO [trainer.py:765] (3/8) Epoch 34, batch 100, train_loss[loss=3.454, NarTop10Accuracy=0.6313, over 7134.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.718, over 2359.05 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,613 INFO [trainer.py:765] (3/8) Epoch 34, batch 200, train_loss[loss=3.158, NarTop10Accuracy=0.6979, over 7053.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7213, over 3835.73 frames. ], batch size: 18, lr: 2.52e-03
2024-08-06 21:57:31,776 INFO [trainer.py:765] (3/8) Epoch 34, batch 300, train_loss[loss=2.765, NarTop10Accuracy=0.765, over 7212.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7179, over 4642.06 frames. ], batch size: 23, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (3/8) Epoch 34, batch 400, train_loss[loss=3.166, NarTop10Accuracy=0.6882, over 5157.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7209, over 5089.76 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,690 INFO [trainer.py:765] (3/8) Epoch 34, batch 500, train_loss[loss=3.263, NarTop10Accuracy=0.677, over 6018.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7192, over 5366.83 frames. ], batch size: 11, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (3/8) Epoch 34, batch 600, train_loss[loss=2.893, NarTop10Accuracy=0.7473, over 5733.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7187, over 5632.97 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,056 INFO [trainer.py:765] (3/8) Epoch 34, batch 700, train_loss[loss=3.025, NarTop10Accuracy=0.7204, over 5037.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7174, over 5714.60 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (3/8) Epoch 34, batch 800, train_loss[loss=3.031, NarTop10Accuracy=0.7133, over 4998.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7189, over 5767.68 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (3/8) Epoch 34, batch 900, train_loss[loss=2.884, NarTop10Accuracy=0.7439, over 6210.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7193, over 5803.86 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:01:25,338 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (3/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:01:34,091 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.819e+02 2.259e+02 2.434e+02 2.615e+02 5.125e+02, threshold=4.868e+02, percent-clipped=0.1
2024-08-06 22:01:35,624 INFO [trainer.py:765] (3/8) Epoch 34, batch 1000, train_loss[loss=3.261, NarTop10Accuracy=0.6726, over 6297.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7182, over 5901.79 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:02:10,829 INFO [trainer.py:765] (3/8) Epoch 34, batch 1100, train_loss[loss=3.405, NarTop10Accuracy=0.6424, over 6849.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7165, over 5942.98 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (3/8) Epoch 34, batch 1200, train_loss[loss=2.848, NarTop10Accuracy=0.7607, over 6897.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 5931.63 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,813 INFO [trainer.py:765] (3/8) Epoch 34, batch 1300, train_loss[loss=2.68, NarTop10Accuracy=0.7953, over 5004.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7169, over 5999.74 frames. ], batch size: 6, lr: 2.50e-03
2024-08-06 22:03:52,949 INFO [trainer.py:765] (3/8) Epoch 34, batch 1400, train_loss[loss=3.287, NarTop10Accuracy=0.6653, over 5946.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 6041.01 frames. ], batch size: 11, lr: 2.50e-03
2024-08-06 22:04:20,822 INFO [trainer.py:765] (3/8) Epoch 34, batch 1500, train_loss[loss=3.061, NarTop10Accuracy=0.7237, over 5730.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 5944.58 frames. ], batch size: 50, lr: 2.50e-03
2024-08-06 22:04:48,599 INFO [trainer.py:765] (3/8) Epoch 34, batch 1600, train_loss[loss=2.937, NarTop10Accuracy=0.7306, over 7143.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5920.51 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (3/8) Epoch 34, batch 1700, train_loss[loss=3.153, NarTop10Accuracy=0.693, over 6315.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7179, over 5921.11 frames. ], batch size: 13, lr: 2.50e-03
2024-08-06 22:05:41,720 INFO [trainer.py:765] (3/8) Epoch 34, batch 1800, train_loss[loss=3.133, NarTop10Accuracy=0.6965, over 7101.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7159, over 5994.05 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,206 INFO [trainer.py:765] (3/8) Epoch 34, batch 1900, train_loss[loss=3.121, NarTop10Accuracy=0.7116, over 6288.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7118, over 6025.04 frames. ], batch size: 51, lr: 2.49e-03
2024-08-06 22:06:33,770 INFO [trainer.py:765] (3/8) Epoch 34, batch 2000, train_loss[loss=3.097, NarTop10Accuracy=0.7064, over 6084.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7149, over 5987.62 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,126 INFO [trainer.py:765] (3/8) Epoch 34, batch 2100, train_loss[loss=2.979, NarTop10Accuracy=0.7187, over 4794.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7121, over 5980.19 frames. ], batch size: 5, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (3/8) Epoch 34, batch 2200, train_loss[loss=2.855, NarTop10Accuracy=0.7548, over 7242.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7125, over 6014.17 frames. ], batch size: 31, lr: 2.49e-03
2024-08-06 22:07:49,535 INFO [trainer.py:765] (3/8) Epoch 34, batch 2300, train_loss[loss=2.675, NarTop10Accuracy=0.789, over 5631.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7124, over 6012.87 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (3/8) Epoch 34, batch 2400, train_loss[loss=3.288, NarTop10Accuracy=0.6646, over 5073.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7144, over 5759.04 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (3/8) Epoch 34, batch 2500, train_loss[loss=2.838, NarTop10Accuracy=0.7673, over 5112.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.72, over 5480.55 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,803 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 22:09:52,640 INFO [trainer.py:765] (3/8) Epoch 35, batch 100, train_loss[loss=2.926, NarTop10Accuracy=0.7424, over 7407.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7159, over 2374.82 frames. ], batch size: 31, lr: 2.45e-03
2024-08-06 22:10:29,697 INFO [trainer.py:765] (3/8) Epoch 35, batch 200, train_loss[loss=3.141, NarTop10Accuracy=0.6962, over 6615.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7153, over 3857.48 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,942 INFO [trainer.py:765] (3/8) Epoch 35, batch 300, train_loss[loss=2.792, NarTop10Accuracy=0.7637, over 7029.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7193, over 4663.44 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (3/8) Epoch 35, batch 400, train_loss[loss=2.964, NarTop10Accuracy=0.7347, over 5016.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7193, over 5109.00 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,048 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (3/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,129 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:11:48,702 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.898e+02 2.275e+02 2.426e+02 2.615e+02 4.095e+02, threshold=4.852e+02, percent-clipped=0.0
2024-08-06 22:12:17,723 INFO [trainer.py:765] (3/8) Epoch 35, batch 500, train_loss[loss=2.813, NarTop10Accuracy=0.7635, over 6177.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7216, over 5395.12 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,424 INFO [trainer.py:765] (3/8) Epoch 35, batch 600, train_loss[loss=3.092, NarTop10Accuracy=0.7124, over 5676.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7183, over 5654.18 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,940 INFO [trainer.py:765] (3/8) Epoch 35, batch 700, train_loss[loss=2.556, NarTop10Accuracy=0.8049, over 5118.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.719, over 5734.25 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:01,383 INFO [trainer.py:765] (3/8) Epoch 35, batch 800, train_loss[loss=2.723, NarTop10Accuracy=0.7817, over 4446.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7177, over 5798.06 frames. ], batch size: 5, lr: 2.44e-03
2024-08-06 22:14:34,372 INFO [trainer.py:765] (3/8) Epoch 35, batch 900, train_loss[loss=3.096, NarTop10Accuracy=0.7028, over 6636.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7206, over 5800.45 frames. ], batch size: 14, lr: 2.44e-03
2024-08-06 22:15:09,372 INFO [trainer.py:765] (3/8) Epoch 35, batch 1000, train_loss[loss=2.853, NarTop10Accuracy=0.7504, over 6675.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.717, over 5896.79 frames. ], batch size: 14, lr: 2.43e-03
2024-08-06 22:15:48,495 INFO [trainer.py:765] (3/8) Epoch 35, batch 1100, train_loss[loss=3.044, NarTop10Accuracy=0.7139, over 6765.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5908.57 frames. ], batch size: 17, lr: 2.43e-03
2024-08-06 22:16:22,483 INFO [trainer.py:765] (3/8) Epoch 35, batch 1200, train_loss[loss=2.897, NarTop10Accuracy=0.7468, over 7509.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7184, over 5923.09 frames. ], batch size: 31, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (3/8) Epoch 35, batch 1300, train_loss[loss=2.74, NarTop10Accuracy=0.765, over 4959.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7207, over 5989.76 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,061 INFO [trainer.py:765] (3/8) Epoch 35, batch 1400, train_loss[loss=3.05, NarTop10Accuracy=0.7214, over 5964.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7182, over 6022.34 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (3/8) Epoch 35, batch 1500, train_loss[loss=3.072, NarTop10Accuracy=0.7161, over 6111.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7175, over 5949.37 frames. ], batch size: 50, lr: 2.43e-03
2024-08-06 22:18:30,728 INFO [trainer.py:765] (3/8) Epoch 35, batch 1600, train_loss[loss=2.909, NarTop10Accuracy=0.7393, over 7026.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7154, over 5932.89 frames. ], batch size: 22, lr: 2.43e-03
2024-08-06 22:18:57,319 INFO [trainer.py:765] (3/8) Epoch 35, batch 1700, train_loss[loss=2.853, NarTop10Accuracy=0.7642, over 6687.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7138, over 5931.41 frames. ], batch size: 14, lr: 2.42e-03
2024-08-06 22:19:23,703 INFO [trainer.py:765] (3/8) Epoch 35, batch 1800, train_loss[loss=3.4, NarTop10Accuracy=0.6455, over 7218.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 5975.41 frames. ], batch size: 22, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (3/8) Epoch 35, batch 1900, train_loss[loss=3.095, NarTop10Accuracy=0.708, over 6252.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 6015.71 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:15,762 INFO [trainer.py:765] (3/8) Epoch 35, batch 2000, train_loss[loss=3.05, NarTop10Accuracy=0.7152, over 6651.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7179, over 5997.75 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:41,045 INFO [trainer.py:765] (3/8) Epoch 35, batch 2100, train_loss[loss=2.759, NarTop10Accuracy=0.7605, over 3852.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7163, over 5965.82 frames. ], batch size: 4, lr: 2.42e-03
2024-08-06 22:21:06,226 INFO [trainer.py:765] (3/8) Epoch 35, batch 2200, train_loss[loss=2.906, NarTop10Accuracy=0.7463, over 7422.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 6011.65 frames. ], batch size: 31, lr: 2.42e-03
2024-08-06 22:21:31,286 INFO [trainer.py:765] (3/8) Epoch 35, batch 2300, train_loss[loss=2.981, NarTop10Accuracy=0.7347, over 6174.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7155, over 6015.05 frames. ], batch size: 10, lr: 2.42e-03
2024-08-06 22:21:55,648 INFO [trainer.py:765] (3/8) Epoch 35, batch 2400, train_loss[loss=3.398, NarTop10Accuracy=0.6478, over 5133.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7172, over 5760.56 frames. ], batch size: 7, lr: 2.42e-03
2024-08-06 22:21:59,682 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (3/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.895e+02 2.316e+02 2.462e+02 2.653e+02 5.566e+02, threshold=4.923e+02, percent-clipped=0.1
2024-08-06 22:22:27,127 INFO [trainer.py:765] (3/8) Epoch 35, batch 2500, train_loss[loss=2.983, NarTop10Accuracy=0.725, over 5004.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7216, over 5465.53 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:47,018 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 22:23:47,172 INFO [trainer.py:765] (3/8) Epoch 36, batch 100, train_loss[loss=3.177, NarTop10Accuracy=0.6969, over 7434.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7266, over 2354.14 frames. ], batch size: 33, lr: 2.38e-03
2024-08-06 22:24:22,495 INFO [trainer.py:765] (3/8) Epoch 36, batch 200, train_loss[loss=2.836, NarTop10Accuracy=0.762, over 6810.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7196, over 3869.39 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,721 INFO [trainer.py:765] (3/8) Epoch 36, batch 300, train_loss[loss=3.126, NarTop10Accuracy=0.6947, over 6969.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7178, over 4683.84 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,276 INFO [trainer.py:765] (3/8) Epoch 36, batch 400, train_loss[loss=2.85, NarTop10Accuracy=0.7556, over 5184.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7219, over 5128.47 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,819 INFO [trainer.py:765] (3/8) Epoch 36, batch 500, train_loss[loss=3.411, NarTop10Accuracy=0.6384, over 6576.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7213, over 5396.81 frames. ], batch size: 12, lr: 2.37e-03
2024-08-06 22:26:35,026 INFO [trainer.py:765] (3/8) Epoch 36, batch 600, train_loss[loss=3.08, NarTop10Accuracy=0.7183, over 6141.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7216, over 5643.71 frames. ], batch size: 10, lr: 2.37e-03
2024-08-06 22:27:10,991 INFO [trainer.py:765] (3/8) Epoch 36, batch 700, train_loss[loss=3.194, NarTop10Accuracy=0.6813, over 5043.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7218, over 5715.95 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:27:44,915 INFO [trainer.py:765] (3/8) Epoch 36, batch 800, train_loss[loss=3.344, NarTop10Accuracy=0.6523, over 4254.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7181, over 5768.29 frames. ], batch size: 5, lr: 2.37e-03
2024-08-06 22:28:17,813 INFO [trainer.py:765] (3/8) Epoch 36, batch 900, train_loss[loss=2.818, NarTop10Accuracy=0.7668, over 6237.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7209, over 5800.07 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:28:56,984 INFO [trainer.py:765] (3/8) Epoch 36, batch 1000, train_loss[loss=3.332, NarTop10Accuracy=0.6552, over 6231.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7202, over 5902.25 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:29:29,365 INFO [trainer.py:765] (3/8) Epoch 36, batch 1100, train_loss[loss=2.784, NarTop10Accuracy=0.7695, over 6897.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7192, over 5932.55 frames. ], batch size: 17, lr: 2.36e-03
2024-08-06 22:30:05,681 INFO [trainer.py:765] (3/8) Epoch 36, batch 1200, train_loss[loss=3.115, NarTop10Accuracy=0.7089, over 7302.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7199, over 5931.15 frames. ], batch size: 31, lr: 2.36e-03
2024-08-06 22:30:42,576 INFO [trainer.py:765] (3/8) Epoch 36, batch 1300, train_loss[loss=2.665, NarTop10Accuracy=0.7836, over 5214.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.719, over 5990.01 frames. ], batch size: 6, lr: 2.36e-03
2024-08-06 22:31:15,939 INFO [trainer.py:765] (3/8) Epoch 36, batch 1400, train_loss[loss=3.072, NarTop10Accuracy=0.697, over 6003.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 6010.62 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,749 INFO [trainer.py:765] (3/8) Epoch 36, batch 1500, train_loss[loss=3.316, NarTop10Accuracy=0.6648, over 6456.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5963.09 frames. ], batch size: 51, lr: 2.36e-03
2024-08-06 22:32:11,460 INFO [trainer.py:765] (3/8) Epoch 36, batch 1600, train_loss[loss=3.411, NarTop10Accuracy=0.6454, over 7140.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7198, over 5936.21 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,109 INFO [trainer.py:765] (3/8) Epoch 36, batch 1700, train_loss[loss=3.35, NarTop10Accuracy=0.6567, over 6321.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7176, over 5929.35 frames. ], batch size: 13, lr: 2.36e-03
2024-08-06 22:33:04,555 INFO [trainer.py:765] (3/8) Epoch 36, batch 1800, train_loss[loss=3.152, NarTop10Accuracy=0.687, over 7035.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7184, over 5992.42 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:33:15,171 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (3/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.876e+02 2.309e+02 2.476e+02 2.664e+02 4.811e+02, threshold=4.951e+02, percent-clipped=0.0
2024-08-06 22:33:39,456 INFO [trainer.py:765] (3/8) Epoch 36, batch 1900, train_loss[loss=3.036, NarTop10Accuracy=0.7226, over 6114.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7176, over 6029.69 frames. ], batch size: 51, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (3/8) Epoch 36, batch 2000, train_loss[loss=3.173, NarTop10Accuracy=0.7014, over 5688.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 5996.88 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:30,514 INFO [trainer.py:765] (3/8) Epoch 36, batch 2100, train_loss[loss=2.864, NarTop10Accuracy=0.7565, over 4731.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 5963.20 frames. ], batch size: 5, lr: 2.35e-03
2024-08-06 22:34:55,938 INFO [trainer.py:765] (3/8) Epoch 36, batch 2200, train_loss[loss=3.324, NarTop10Accuracy=0.6501, over 7215.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7154, over 5995.51 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,145 INFO [trainer.py:765] (3/8) Epoch 36, batch 2300, train_loss[loss=3.4, NarTop10Accuracy=0.6535, over 5748.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 6011.78 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,601 INFO [trainer.py:765] (3/8) Epoch 36, batch 2400, train_loss[loss=3.296, NarTop10Accuracy=0.6601, over 5091.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7166, over 5793.41 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,183 INFO [trainer.py:765] (3/8) Epoch 36, batch 2500, train_loss[loss=2.802, NarTop10Accuracy=0.7617, over 5079.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7211, over 5496.09 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:29,223 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 22:37:29,726 INFO [trainer.py:765] (3/8) Epoch 37, batch 100, train_loss[loss=2.821, NarTop10Accuracy=0.7546, over 7305.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7145, over 2349.49 frames. ], batch size: 31, lr: 2.31e-03
2024-08-06 22:38:01,273 INFO [trainer.py:765] (3/8) Epoch 37, batch 200, train_loss[loss=2.801, NarTop10Accuracy=0.7785, over 6942.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7204, over 3838.30 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,956 INFO [trainer.py:765] (3/8) Epoch 37, batch 300, train_loss[loss=3.159, NarTop10Accuracy=0.6963, over 6948.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7212, over 4626.07 frames. ], batch size: 22, lr: 2.31e-03
2024-08-06 22:39:09,307 INFO [trainer.py:765] (3/8) Epoch 37, batch 400, train_loss[loss=2.599, NarTop10Accuracy=0.8066, over 5049.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7242, over 5072.69 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,862 INFO [trainer.py:765] (3/8) Epoch 37, batch 500, train_loss[loss=3.476, NarTop10Accuracy=0.6248, over 6078.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7236, over 5362.96 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,334 INFO [trainer.py:765] (3/8) Epoch 37, batch 600, train_loss[loss=2.747, NarTop10Accuracy=0.786, over 5778.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7224, over 5634.00 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,616 INFO [trainer.py:765] (3/8) Epoch 37, batch 700, train_loss[loss=3.098, NarTop10Accuracy=0.7075, over 5148.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 5722.40 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:30,565 INFO [trainer.py:765] (3/8) Epoch 37, batch 800, train_loss[loss=2.742, NarTop10Accuracy=0.7852, over 4977.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7179, over 5779.95 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,084 INFO [trainer.py:765] (3/8) Epoch 37, batch 900, train_loss[loss=2.994, NarTop10Accuracy=0.7302, over 6297.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7208, over 5791.03 frames. ], batch size: 13, lr: 2.30e-03
2024-08-06 22:42:38,268 INFO [trainer.py:765] (3/8) Epoch 37, batch 1000, train_loss[loss=3.133, NarTop10Accuracy=0.7034, over 6573.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7181, over 5893.55 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:43:15,907 INFO [trainer.py:765] (3/8) Epoch 37, batch 1100, train_loss[loss=3.074, NarTop10Accuracy=0.7159, over 6801.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7173, over 5909.87 frames. ], batch size: 17, lr: 2.30e-03
2024-08-06 22:43:47,740 INFO [trainer.py:765] (3/8) Epoch 37, batch 1200, train_loss[loss=2.917, NarTop10Accuracy=0.7538, over 7443.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5907.39 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,755 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (3/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,076 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:44:20,606 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.887e+02 2.309e+02 2.481e+02 2.647e+02 8.766e+02, threshold=4.961e+02, percent-clipped=0.1
2024-08-06 22:44:32,784 INFO [trainer.py:765] (3/8) Epoch 37, batch 1300, train_loss[loss=2.789, NarTop10Accuracy=0.7732, over 5082.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7196, over 5972.93 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:45:10,388 INFO [trainer.py:765] (3/8) Epoch 37, batch 1400, train_loss[loss=2.661, NarTop10Accuracy=0.8055, over 6150.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7206, over 6033.85 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,513 INFO [trainer.py:765] (3/8) Epoch 37, batch 1500, train_loss[loss=2.971, NarTop10Accuracy=0.7399, over 5982.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7183, over 5961.09 frames. ], batch size: 51, lr: 2.29e-03
2024-08-06 22:46:08,438 INFO [trainer.py:765] (3/8) Epoch 37, batch 1600, train_loss[loss=3.456, NarTop10Accuracy=0.6334, over 7146.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7161, over 5937.96 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,187 INFO [trainer.py:765] (3/8) Epoch 37, batch 1700, train_loss[loss=3.343, NarTop10Accuracy=0.6477, over 6714.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7179, over 5930.49 frames. ], batch size: 14, lr: 2.29e-03
2024-08-06 22:47:01,793 INFO [trainer.py:765] (3/8) Epoch 37, batch 1800, train_loss[loss=2.764, NarTop10Accuracy=0.7753, over 7365.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7185, over 5995.96 frames. ], batch size: 23, lr: 2.29e-03
2024-08-06 22:47:28,312 INFO [trainer.py:765] (3/8) Epoch 37, batch 1900, train_loss[loss=3.055, NarTop10Accuracy=0.717, over 5916.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7176, over 6013.54 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:47:53,925 INFO [trainer.py:765] (3/8) Epoch 37, batch 2000, train_loss[loss=3.233, NarTop10Accuracy=0.6655, over 5985.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7192, over 5974.69 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:48:19,325 INFO [trainer.py:765] (3/8) Epoch 37, batch 2100, train_loss[loss=2.87, NarTop10Accuracy=0.7457, over 3948.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.718, over 5956.77 frames. ], batch size: 4, lr: 2.29e-03
2024-08-06 22:48:44,708 INFO [trainer.py:765] (3/8) Epoch 37, batch 2200, train_loss[loss=2.941, NarTop10Accuracy=0.736, over 7407.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 6015.62 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,913 INFO [trainer.py:765] (3/8) Epoch 37, batch 2300, train_loss[loss=2.787, NarTop10Accuracy=0.7806, over 5853.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.716, over 6024.07 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,318 INFO [trainer.py:765] (3/8) Epoch 37, batch 2400, train_loss[loss=3.272, NarTop10Accuracy=0.6803, over 5229.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7195, over 5773.10 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,860 INFO [trainer.py:765] (3/8) Epoch 37, batch 2500, train_loss[loss=3.28, NarTop10Accuracy=0.6624, over 5058.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.7261, over 5448.22 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:18,339 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 22:51:16,152 INFO [trainer.py:765] (3/8) Epoch 38, batch 100, train_loss[loss=2.966, NarTop10Accuracy=0.7248, over 7281.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7215, over 2362.53 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,015 INFO [trainer.py:765] (3/8) Epoch 38, batch 200, train_loss[loss=3.234, NarTop10Accuracy=0.6833, over 6825.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7206, over 3843.40 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,203 INFO [trainer.py:765] (3/8) Epoch 38, batch 300, train_loss[loss=2.913, NarTop10Accuracy=0.7453, over 7080.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7185, over 4643.94 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (3/8) Epoch 38, batch 400, train_loss[loss=3.194, NarTop10Accuracy=0.6793, over 5151.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7201, over 5091.59 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,229 INFO [trainer.py:765] (3/8) Epoch 38, batch 500, train_loss[loss=2.811, NarTop10Accuracy=0.7723, over 6072.00 frames. ], tot_loss[loss=2.988, NarTop10Accuracy=0.7275, over 5384.22 frames. ], batch size: 11, lr: 2.25e-03
2024-08-06 22:54:05,498 INFO [trainer.py:765] (3/8) Epoch 38, batch 600, train_loss[loss=3.205, NarTop10Accuracy=0.6781, over 5781.00 frames. ], tot_loss[loss=3.001, NarTop10Accuracy=0.725, over 5655.67 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,004 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (3/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.880e+02 2.313e+02 2.478e+02 2.663e+02 7.254e+02, threshold=4.957e+02, percent-clipped=0.3
2024-08-06 22:54:46,659 INFO [trainer.py:765] (3/8) Epoch 38, batch 700, train_loss[loss=2.749, NarTop10Accuracy=0.7673, over 5067.00 frames. ], tot_loss[loss=3.005, NarTop10Accuracy=0.7242, over 5706.18 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,938 INFO [trainer.py:765] (3/8) Epoch 38, batch 800, train_loss[loss=2.934, NarTop10Accuracy=0.7355, over 5040.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7209, over 5759.03 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,704 INFO [trainer.py:765] (3/8) Epoch 38, batch 900, train_loss[loss=2.834, NarTop10Accuracy=0.7597, over 6669.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7214, over 5779.56 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:56:32,091 INFO [trainer.py:765] (3/8) Epoch 38, batch 1000, train_loss[loss=3.241, NarTop10Accuracy=0.6681, over 6543.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7205, over 5867.07 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:57:08,991 INFO [trainer.py:765] (3/8) Epoch 38, batch 1100, train_loss[loss=3.171, NarTop10Accuracy=0.6833, over 7041.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7176, over 5908.26 frames. ], batch size: 18, lr: 2.24e-03
2024-08-06 22:57:42,662 INFO [trainer.py:765] (3/8) Epoch 38, batch 1200, train_loss[loss=2.858, NarTop10Accuracy=0.755, over 7068.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7187, over 5916.31 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,546 INFO [trainer.py:765] (3/8) Epoch 38, batch 1300, train_loss[loss=3.259, NarTop10Accuracy=0.6743, over 5160.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7199, over 5987.15 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,811 INFO [trainer.py:765] (3/8) Epoch 38, batch 1400, train_loss[loss=2.866, NarTop10Accuracy=0.7562, over 6102.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 6027.43 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,854 INFO [trainer.py:765] (3/8) Epoch 38, batch 1500, train_loss[loss=3.557, NarTop10Accuracy=0.6068, over 6729.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7195, over 5976.90 frames. ], batch size: 53, lr: 2.23e-03
2024-08-06 22:59:50,644 INFO [trainer.py:765] (3/8) Epoch 38, batch 1600, train_loss[loss=3.385, NarTop10Accuracy=0.6462, over 7134.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7187, over 5957.81 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,316 INFO [trainer.py:765] (3/8) Epoch 38, batch 1700, train_loss[loss=2.906, NarTop10Accuracy=0.737, over 6192.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7154, over 5940.31 frames. ], batch size: 13, lr: 2.23e-03
2024-08-06 23:00:43,764 INFO [trainer.py:765] (3/8) Epoch 38, batch 1800, train_loss[loss=3.364, NarTop10Accuracy=0.6519, over 7086.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7164, over 6001.82 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:01:10,193 INFO [trainer.py:765] (3/8) Epoch 38, batch 1900, train_loss[loss=3.458, NarTop10Accuracy=0.6393, over 5940.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 6041.34 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:01:35,681 INFO [trainer.py:765] (3/8) Epoch 38, batch 2000, train_loss[loss=3.247, NarTop10Accuracy=0.6776, over 6411.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7152, over 5996.83 frames. ], batch size: 51, lr: 2.23e-03
2024-08-06 23:02:01,051 INFO [trainer.py:765] (3/8) Epoch 38, batch 2100, train_loss[loss=2.841, NarTop10Accuracy=0.7541, over 4797.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5990.93 frames. ], batch size: 5, lr: 2.23e-03
2024-08-06 23:02:26,314 INFO [trainer.py:765] (3/8) Epoch 38, batch 2200, train_loss[loss=2.842, NarTop10Accuracy=0.7589, over 7305.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7174, over 6010.44 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,420 INFO [trainer.py:765] (3/8) Epoch 38, batch 2300, train_loss[loss=2.63, NarTop10Accuracy=0.8007, over 5769.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7182, over 6006.23 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,348 INFO [trainer.py:765] (3/8) Epoch 38, batch 2400, train_loss[loss=2.909, NarTop10Accuracy=0.739, over 5244.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7196, over 5787.56 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,824 INFO [trainer.py:765] (3/8) Epoch 38, batch 2500, train_loss[loss=3.174, NarTop10Accuracy=0.6776, over 5217.00 frames. ], tot_loss[loss=3.004, NarTop10Accuracy=0.7238, over 5467.54 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:59,877 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 23:04:58,941 INFO [trainer.py:765] (3/8) Epoch 39, batch 100, train_loss[loss=3.286, NarTop10Accuracy=0.6665, over 6975.00 frames. ], tot_loss[loss=2.992, NarTop10Accuracy=0.7273, over 2368.65 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,469 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (3/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 29618MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.911e+02 2.316e+02 2.500e+02 2.688e+02 4.683e+02, threshold=5.001e+02, percent-clipped=0.0
2024-08-06 23:05:40,163 INFO [trainer.py:765] (3/8) Epoch 39, batch 200, train_loss[loss=2.792, NarTop10Accuracy=0.7795, over 6720.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7249, over 3862.18 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (3/8) Epoch 39, batch 300, train_loss[loss=3.024, NarTop10Accuracy=0.721, over 6933.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.7262, over 4661.02 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,276 INFO [trainer.py:765] (3/8) Epoch 39, batch 400, train_loss[loss=2.917, NarTop10Accuracy=0.7489, over 5355.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.7274, over 5110.41 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (3/8) Epoch 39, batch 500, train_loss[loss=3.359, NarTop10Accuracy=0.6588, over 6099.00 frames. ], tot_loss[loss=3.004, NarTop10Accuracy=0.7249, over 5384.82 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (3/8) Epoch 39, batch 600, train_loss[loss=2.652, NarTop10Accuracy=0.8027, over 5709.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7216, over 5659.00 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,695 INFO [trainer.py:765] (3/8) Epoch 39, batch 700, train_loss[loss=3.257, NarTop10Accuracy=0.6738, over 4992.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7199, over 5711.41 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (3/8) Epoch 39, batch 800, train_loss[loss=2.687, NarTop10Accuracy=0.7942, over 4956.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7197, over 5776.20 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:38,865 INFO [trainer.py:765] (3/8) Epoch 39, batch 900, train_loss[loss=3.361, NarTop10Accuracy=0.6438, over 6639.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7212, over 5782.52 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (3/8) Epoch 39, batch 1000, train_loss[loss=2.817, NarTop10Accuracy=0.7595, over 6609.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5916.42 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (3/8) Epoch 39, batch 1100, train_loss[loss=2.753, NarTop10Accuracy=0.7737, over 6786.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7194, over 5926.39 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (3/8) Epoch 39, batch 1200, train_loss[loss=2.919, NarTop10Accuracy=0.7437, over 7344.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7215, over 5926.91 frames. ], batch size: 32, lr: 2.18e-03
2024-08-06 23:12:07,253 INFO [trainer.py:765] (3/8) Epoch 39, batch 1300, train_loss[loss=2.747, NarTop10Accuracy=0.7682, over 5133.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.723, over 6001.36 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,302 INFO [trainer.py:765] (3/8) Epoch 39, batch 1400, train_loss[loss=2.965, NarTop10Accuracy=0.7404, over 6186.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.721, over 6014.42 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (3/8) Epoch 39, batch 1500, train_loss[loss=3.553, NarTop10Accuracy=0.6183, over 6045.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7208, over 5947.62 frames. ], batch size: 50, lr: 2.18e-03
2024-08-06 23:13:37,586 INFO [trainer.py:765] (3/8) Epoch 39, batch 1600, train_loss[loss=2.97, NarTop10Accuracy=0.7342, over 7095.00 frames. ], tot_loss[loss=3.006, NarTop10Accuracy=0.7241, over 5932.73 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:04,220 INFO [trainer.py:765] (3/8) Epoch 39, batch 1700, train_loss[loss=3.419, NarTop10Accuracy=0.6449, over 6696.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7181, over 5914.39 frames. ], batch size: 14, lr: 2.17e-03
2024-08-06 23:14:30,768 INFO [trainer.py:765] (3/8) Epoch 39, batch 1800, train_loss[loss=2.842, NarTop10Accuracy=0.7641, over 6885.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7173, over 5977.41 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,180 INFO [trainer.py:765] (3/8) Epoch 39, batch 1900, train_loss[loss=2.981, NarTop10Accuracy=0.7291, over 6036.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7152, over 6026.64 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:22,751 INFO [trainer.py:765] (3/8) Epoch 39, batch 2000, train_loss[loss=3.258, NarTop10Accuracy=0.6723, over 6111.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5993.49 frames. ], batch size: 51, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (3/8) Epoch 39, batch 2100, train_loss[loss=3.257, NarTop10Accuracy=0.6732, over 4809.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7195, over 5965.55 frames. ], batch size: 5, lr: 2.17e-03
2024-08-06 23:15:51,871 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (3/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,156 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 30367MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.940e+02 2.369e+02 2.530e+02 2.720e+02 6.127e+02, threshold=5.059e+02, percent-clipped=0.2
2024-08-06 23:16:23,652 INFO [trainer.py:765] (3/8) Epoch 39, batch 2200, train_loss[loss=3.228, NarTop10Accuracy=0.6752, over 7377.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7197, over 6011.15 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,847 INFO [trainer.py:765] (3/8) Epoch 39, batch 2300, train_loss[loss=2.872, NarTop10Accuracy=0.7571, over 5742.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7171, over 6027.38 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,136 INFO [trainer.py:765] (3/8) Epoch 39, batch 2400, train_loss[loss=2.656, NarTop10Accuracy=0.7924, over 5061.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7218, over 5779.35 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,711 INFO [trainer.py:765] (3/8) Epoch 39, batch 2500, train_loss[loss=2.861, NarTop10Accuracy=0.7513, over 5037.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7259, over 5472.13 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,449 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 23:18:48,946 INFO [trainer.py:765] (3/8) Epoch 40, batch 100, train_loss[loss=2.999, NarTop10Accuracy=0.7225, over 7410.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.723, over 2385.22 frames. ], batch size: 31, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (3/8) Epoch 40, batch 200, train_loss[loss=2.857, NarTop10Accuracy=0.7473, over 6684.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.7268, over 3868.60 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,187 INFO [trainer.py:765] (3/8) Epoch 40, batch 300, train_loss[loss=2.834, NarTop10Accuracy=0.7551, over 7191.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7234, over 4664.94 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (3/8) Epoch 40, batch 400, train_loss[loss=2.91, NarTop10Accuracy=0.7472, over 4965.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7235, over 5113.54 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,250 INFO [trainer.py:765] (3/8) Epoch 40, batch 500, train_loss[loss=2.841, NarTop10Accuracy=0.7587, over 6153.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7235, over 5395.15 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,881 INFO [trainer.py:765] (3/8) Epoch 40, batch 600, train_loss[loss=2.773, NarTop10Accuracy=0.7672, over 5586.00 frames. ], tot_loss[loss=3.001, NarTop10Accuracy=0.725, over 5654.68 frames. ], batch size: 9, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (3/8) Epoch 40, batch 700, train_loss[loss=3.111, NarTop10Accuracy=0.7002, over 5163.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7234, over 5729.47 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,753 INFO [trainer.py:765] (3/8) Epoch 40, batch 800, train_loss[loss=2.797, NarTop10Accuracy=0.7628, over 5115.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7211, over 5776.69 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,635 INFO [trainer.py:765] (3/8) Epoch 40, batch 900, train_loss[loss=3.358, NarTop10Accuracy=0.6557, over 6393.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7218, over 5786.99 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:23:55,591 INFO [trainer.py:765] (3/8) Epoch 40, batch 1000, train_loss[loss=3.388, NarTop10Accuracy=0.6442, over 6273.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7208, over 5897.37 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (3/8) Epoch 40, batch 1100, train_loss[loss=2.763, NarTop10Accuracy=0.7694, over 7011.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7206, over 5930.92 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (3/8) Epoch 40, batch 1200, train_loss[loss=2.909, NarTop10Accuracy=0.7395, over 7071.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7204, over 5938.08 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,842 INFO [trainer.py:765] (3/8) Epoch 40, batch 1300, train_loss[loss=2.732, NarTop10Accuracy=0.7726, over 5073.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7228, over 5989.56 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,384 INFO [trainer.py:765] (3/8) Epoch 40, batch 1400, train_loss[loss=2.787, NarTop10Accuracy=0.775, over 6159.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7203, over 6007.31 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (3/8) Epoch 40, batch 1500, train_loss[loss=3.196, NarTop10Accuracy=0.6817, over 5871.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7227, over 5936.05 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:26:54,419 INFO [trainer.py:803] (3/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (3/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (3/8) Maximum memory allocated so far is 30367MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (3/8) Clipping_scale=2.0, grad-norm quartiles 1.941e+02 2.329e+02 2.511e+02 2.723e+02 1.241e+03, threshold=5.022e+02, percent-clipped=0.2
2024-08-06 23:27:19,382 INFO [trainer.py:765] (3/8) Epoch 40, batch 1600, train_loss[loss=2.95, NarTop10Accuracy=0.7356, over 6984.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7211, over 5926.73 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,056 INFO [trainer.py:765] (3/8) Epoch 40, batch 1700, train_loss[loss=3.396, NarTop10Accuracy=0.6433, over 6285.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7221, over 5923.04 frames. ], batch size: 13, lr: 2.12e-03
2024-08-06 23:28:12,578 INFO [trainer.py:765] (3/8) Epoch 40, batch 1800, train_loss[loss=2.986, NarTop10Accuracy=0.7188, over 7038.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.7259, over 5993.16 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,909 INFO [trainer.py:765] (3/8) Epoch 40, batch 1900, train_loss[loss=3.114, NarTop10Accuracy=0.7006, over 5964.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7247, over 6028.79 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,444 INFO [trainer.py:765] (3/8) Epoch 40, batch 2000, train_loss[loss=3.529, NarTop10Accuracy=0.6164, over 5595.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7232, over 6000.07 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:29,750 INFO [trainer.py:765] (3/8) Epoch 40, batch 2100, train_loss[loss=2.75, NarTop10Accuracy=0.7702, over 4011.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7232, over 5980.47 frames. ], batch size: 4, lr: 2.11e-03
2024-08-06 23:29:54,939 INFO [trainer.py:765] (3/8) Epoch 40, batch 2200, train_loss[loss=3.225, NarTop10Accuracy=0.6751, over 7080.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7202, over 6012.18 frames. ], batch size: 31, lr: 2.11e-03
2024-08-06 23:30:20,012 INFO [trainer.py:765] (3/8) Epoch 40, batch 2300, train_loss[loss=2.856, NarTop10Accuracy=0.7473, over 5622.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7189, over 6024.47 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,295 INFO [trainer.py:765] (3/8) Epoch 40, batch 2400, train_loss[loss=2.692, NarTop10Accuracy=0.7959, over 5097.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7205, over 5757.58 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (3/8) Epoch 40, batch 2500, train_loss[loss=3.073, NarTop10Accuracy=0.7086, over 5322.00 frames. ], tot_loss[loss=2.984, NarTop10Accuracy=0.7283, over 5476.77 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,485 INFO [trainer.py:650] (3/8) Reaches end of dataloader.
2024-08-06 23:31:27,488 INFO [trainer.py:1069] (3/8) Done!